{
  "test_bleu_4": 0.0076212802206186364,
  "test_exact_match": 0.0,
  "test_rouge": {
    "rouge1": 0.1262131629138889,
    "rouge2": 0.014314097112991597,
    "rougeL": 0.10787580614917633,
    "rougeLsum": 0.10782945771237183
  },
  "test_bertscore": {
    "precision": 0.8560698860713146,
    "recall": 0.8320607300212173,
    "f1": 0.843511113862347
  },
  "test_meteor": 0.0857942521443964,
  "raw_data": [
    {
      "prediction": "I think this is a hack.",
      "reference": "can we also test for `transport=rest`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If record_batch_size is not set in config.ini, this code will trigger a notice about an undefined value. I would suggest either wrapping the setPageSize() call in an `if (!empty(...)) {` check, or else providing a default value in the set call (i.e. `$config->Index->record_batch_size ?? 100`)."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I didn't realize we were hardcoding this, thanks for moving it to an env value."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We are trying to support IE 10-11, so we'll need a polyfill for this one, I think."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It looks like there's a new `isNavigatingTo( url )` selector for this very purpose so let's use this here instead. This way we just need to use the one selector rather than two. Let's assign that to a similar-named variable here (e.g. `isNavigatingToPostResetURL`) rather than the prop it's used with."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think im2col should only accommodate CPUMat."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "alpha sort the imports"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Can you explain why is this necessary? Is `snprintf()` with four integer arguments unsafe?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "How likely would it be that the keyboard layout for the NVDA main thread differs from the keyboard layout of the currently focused app?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Would you mind removing the default parameter above? (I doubt I'll ever use defaults again since you still have to protect against callers explicitly passing `null` or `undefined`)"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the right thing to do with the `sendKeys()` method.",
      "reference": "Also update line 2205 below"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "n_: It is a good practice to name the variable to indicate what they contain. In this case since `shared` is supposed to have boolean, calling it: `isShared` can help in the readability of the code."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `freezeColumn()` method.",
      "reference": "I suppose it's a false-positive error. Maybe there is a way to configure the `eslint-*` package to accept `i.e. .... lower case` syntax  "
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this maynot be a perf issue, if ToHexString() is not actually allocating a string, but returns the caches string value. to be confirmed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`zap.String(\"image-provider\", provider.Name())` should be in a same line."
    },
    {
      "prediction": "I'm not sure if it's a string, but I'm not sure if it's a string.",
      "reference": "Why this deletion?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change looks unrelated to the CL description?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not certain that `res`+`utl` isn't a thing."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This method can cause bugs. Why don't you use list of finalize statuses and then use join by comma and that will give you correct value. Use Apache Commons Lang library List<Integer> list = Arrays.asList(1,2,3,4,5,6,7); String str = org.apache.commons.lang.StringUtils.join(list, \",\"); You can use it at multiple places shown in this diff."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Merge with next condition"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe add it when it is used."
    },
    {
      "prediction": "I don't think we want to use `non_exist_scanner` here, but I don't think we want to use `non_exist_scanner` here, but I don't think we want to use `non_exist_scanner` here.",
      "reference": "More clear naming: NONEXISTENT_ENABLED"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "why is this change necessary?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "make a SchemaTypeNameConverter.getTypeNameForEmptyType() and call that here."
    },
    {
      "prediction": "I'm not sure why this is the default language? I'm not sure if this is the default language?",
      "reference": "Use braces on your conditional structures please"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Great God, I have a question. This \".nebula_history\" file is used to save history commands. Is there a file size limit? When the file is large, does it take a long time to start initialization (loadHistory)? How did you think about this? Thx."
    },
    {
      "prediction": "I think this should be removed.",
      "reference": "Isn't this the same check as two lines above?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `config.yaml`?",
      "reference": "Don't redefine, just import the existing one in `cmdline.py`. :)"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "why not call `respond_to?(\"#{name}=\")` from the `if` line?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the working directory?",
      "reference": "This was properly set above as `<target>.runfiles/<workspace_name>` (with a fallback to workspace root dir) but never used past this line."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Are all these namespaces required for this attribute?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Given this may be used and printed in other ways, isn't `debug` more appropriate?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like this is unused? Did you mean to call it when clearing the block journal?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "why named alters? how about this.alerts = alerts?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "not sure if this has to be here or not tbh"
    },
    {
      "prediction": "This is a hack.",
      "reference": "There's a better fix for this in #1741, which should replace this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Use swarm.Address not []byte as type, and construct it from actual byteslice or use swarm.NewAddress if it is constructed from hex-encoded string."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It would be worth factoring this out to a function, but you don't have to do that here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "There's no need for `final` in interfaces."
    },
    {
      "prediction": "I don't think this is a bug in Datadog.Trace.OpenTracing.",
      "reference": "Isn't this case handled as a custom tag in `Span.SetTag()` below? This switch is only for special tags that actually set `Span` properties."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "This shouldn't be changed."
    },
    {
      "prediction": "This file is part of Invenio. This file is part of Invenio. This file is part of Invenio. This file is part of Invenio. This file is part of Invenio. This file is part of Invenio. This file is part of Invenio. This file is part of Invenio. This file is part of Invenio. This file is part of Invenio. This file is part of Invenio.",
      "reference": "This one is important `2: I102 copyright year is outdated, expected 2014 but got 2012`"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Are these imports needed (BiConsumer and Consumer)? If they are unused imports, then precommit will fail."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Why are we catching and logging exceptions? By doing that we make it look like the job has succeeded and it will be removed from the queue - if we didn't do that then it would stay queued..."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "If there are `@param` tags in docblock, there should be `@return` tag also. (applies for a whole file)"
    },
    {
      "prediction": "I think this is the default metric category.",
      "reference": "Is the concept of validators exclusive to IBFT2? I wonder if this category should be more explicitly linked to IBFT2."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Spotless is configured to reject star imports. Please replace with explicit imports."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Remind me why you are using CUDA vocabulary when naming these variables."
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please turn the iteration order around (instead of `0...size` to `size...0`). The reason is that this sometimes skips indices when removing an item. You can therefore end up with feeds that have counter 0 and are still displayed."
    },
    {
      "prediction": "This is a hack.",
      "reference": "this is a behavior change. solid_subset=[] represents an empty pipeline where as solid_subset=None is the full pipeline"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "this is a breaking change, any specific reason you want to do this?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Blocking: we still want read write separation. Node functions should absolutely not write to the chain store and the interface should reflect that. Only the syncer should have this capability in production code. It should be no problem to keep casting chainForTest to a read-write interface, or doing other function decomposition and automatic casting tricks."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "The PR description says the lowest on-demand request priority is `2^30`. Why the `-1` here?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "checking health again? I think it is not necessary."
    },
    {
      "prediction": "I think this should be done in the future.",
      "reference": "Need an `if err == nil {break}` above this line so that we don't log/sleep if the retry succeeds."
    },
    {
      "prediction": "I'm not sure if this is a `Promise` object, but it's not a `Promise` object, but it's not a `Promise` object.",
      "reference": "to reiterate my point above, this class is not the actual provided Promise, but rather something a user can provide a Promise to/with. I think a name like `PromiseProvider` is more appropriate."
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "I guess we can only call this from a post-build function, but we might need to check that this target is to be built? I guess target A depends on B which has a post build. We `plz build :B` which adds C as a dep of A. Won't we queue C to be built even though it only needs to build if A needs to be built? That's kinda why I approached this the way I did. I trust you've thought about this but would be good to understand this a bit better."
    },
    {
      "prediction": "I don't think we want to use select.select(outmask, [], [], 0.05)",
      "reference": "You should use `isinstance()` instead of comparing the class name to a string."
    },
    {
      "prediction": "I don't think this is the case for `video` or `audio` el's, but it's not the case for `audio` el's.",
      "reference": "Why should audio and video elements always return `false` for `isHidden`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This obviously won't work for all the other platforms."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Isn't he diamond operator Java7+?"
    },
    {
      "prediction": "I don't think the message is null?",
      "reference": "Prefer adding a second `positive(String, double)` that delegates down to this three-param version. Using `null` in code is generally Not A Great Idea, and it looks ugly."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This pattern, where we add a new parameter without using it, often indicates to me that we've got a leaky interface or abstraction. I see this pattern _a lot_ in this patch, so wondering you have thoughts about it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This seems like an improved pattern :)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "`open_id_authentication` is no longer the name of the function, and it's not OpenID specific"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This didn't require corresponding changes to the test case(s)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "A question! I think `string` totally works, but what do you think of `*string` for consistency?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Should this be: `aws.infrastructure.cluster.sigs.k8s.io` instead?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Not clear on why this change is correct."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Hi Simon. Whether this should return true depends on what byte buffers are used? The same applies to ByteBufferIndexInput, actually... I don't think you can generally tell whether the ByteBuffers the input operates on come from a mmap call or from somewhere else (even direct buffers don't have to be a result of mmap)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "All stories in this file also need to have the default padding."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I don't think these asserts are necessary, because `subsurface_find_sibling` already searches in the parent. Or am I missing something?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `published_on` field.",
      "reference": "Should this be `number` instead of `id`?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "I have forgotten why we thought this restriction is necessary. A user registers a Hive/HBase table with us but is not able to use the table with the registered name in DML. Will UPDATE STATs will be on the original name too (and update stats code will find out registered name and use it for Table_uid?). This was the registration concept is almost like an internal implementation idea, at some point could even be done by some utility program for all existing Hive/hBase tables, and the user need not be aware of it? I am struggling with a user would want to register a table, if they cannot use it by that name."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Should most of these non-globals be static?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please do not approve PRs without tests!!!!"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Now that you handle this in `webenginetab.py` you can undo all the changes in this file."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think we should log the exception to a log file instead of printing it. The current behavior (not catching the exception) should lead to an automatic print of the exception to the terminal/console."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "These changes to the resource helpers have some more far-reaching implications as they also affect calls made in hive-operator, I believe. It's probably OK still, though. Ideally, the resource helper would not be the one doing the logging, since it cannot know the severity, but that is well beyond something that we should tackle for this PR. I would rather have the hive-operator log warnings than have the syncsetinstance controller log errors."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "do you really want to change the behavior on foreign key ?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Looks like my bad. Thanks for fixing!"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I think \"Don't replace variables ...\" would be cleaner."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Do you validate the possible strings? I've not read the code below but we should make sure if a string is supplied it is validate..."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I'd recommend using generateDataDiskName here as well -- might as well benefit from the safety that it gives to protect yourself from future changes to w.ID()."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "qq: do we want to include anything in the name to indicate that it is a position in the manifest?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `mWindows.resumeCompositor()` method.",
      "reference": "These logs should probably use the `LOGTAG`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `wireguard-go/device` and `wireguard-go/tun`?",
      "reference": "From this, it was clear, that we are using our version of wireguard-go. And now it looks like we are using original packages which is confusing."
    },
    {
      "prediction": "I think this is a bug in Nethermind.JsonRpc.",
      "reference": "Any particular reason for this? This potentially will make harder to investigate users issues"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `highlightedConnection` and `localConnection` properties.",
      "reference": "Do you also need to check if Blockly.localConnection_ is non-null?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Not really a container, and it's not just about non-config data, not sure of a better description, @myronmarston ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The desktop app will load this fine. on iOS I get `TypeError: undefined is not an object (evaluating '_$$_REQUIRE(_dependencyMap[8], \"stream\").Readable.Readable')` if I change it to `const Readable = require('stream').Readable;` or `const { Readable } = require('stream');` I get undefined errors from the stream on iOS: `[TypeError: stream.on is not a function. (In 'stream.on(\"data\", function (chunk) { return chunks.push(chunk); })', 'stream.on' is undefined)]` What am I missing?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is needed since the chunk feeder shares memory across calls to the pipeline. this is in order to avoid multiple allocations. this change mimics the behavior of shed and localstore, and copies the data from the call into the in-memory store"
    },
    {
      "prediction": "I don't think this should be used in tests.",
      "reference": "wut. We can do this at the beginning of tests if we want right? Why are we depending on init?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same trick here IMO."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `origin` argument.",
      "reference": "Should be `@origin = element || origin || POINTER`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `--spc-name <spc-name>` option.",
      "reference": "this example needs a fix?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with a list of popups.",
      "reference": "Is it safe to assume this surface is a toplevel?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "we don't need that function"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "we'll also have to think about adding \"Windows Server 2014\" or whatever they come up with later."
    },
    {
      "prediction": "I don't think this is the case for the `fetchActiveFlowByExecId` method, but it's not the case for the `fetchActiveFlowByExecId` method, but it's not the case for the `fetchActiveFlowByExecId` method.",
      "reference": "curious do we have an API to fetch an inactive flow?"
    },
    {
      "prediction": "I don't think this is the case for `obj` and `obj.props` and `obj.props.children`",
      "reference": "This branch is not needed anymore because every `vnode` that passes through `h` in compat or core will have the `$$typeof`-property now ."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `aria-hidden` attribute?",
      "reference": "Did you mean to use `hasAttribute`? You shouldn't. This does not improve performance and it messes with the readability."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `PyQt5.QtCore` module.",
      "reference": "Please import modules and not classes (except for Qt stuff)."
    },
    {
      "prediction": "I'm not sure if this is a real node, but it's not a real node.",
      "reference": "Hm... why do we have a \"DummyJavaNode\" in src/main? Looks like, this should have gone into src/test...."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This seems meaningless. If we cannot add any info let us remove this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you rename `Ports` to `PortsUnsafe`?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "This feels like it could be moved out to your first gem!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The expected behaviour for `poll` would be to match what `Deque` does, which is: > Retrieves and removes the head of the queue represented by this deque As such, you shouldn't need the `RequestId` here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is super minor, but it'd be nice if this iterated over an arbitrary number of array inputs."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here, but I'm not sure why this is the right thing to do.",
      "reference": "What is the problem here? The commit message has strange wording \"readlink is defined with restrict pointers\": do you mean \"restricted\"? Is that a well-defined language term? I'm not sure what it means."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Why are we not wrapping here?"
    },
    {
      "prediction": "I'm not sure why this is a class, but it's not a class. I'm not sure why this is a class. I'm not sure why this is a class.",
      "reference": "I though that all data objects are being unified in the fashion where all default values are initialized in constructor, are not they?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Does this file actually need to be committed to git? Having to run `make generate` is rather tedious on each PR and it conflicts easily."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't need this anymore, as Google's library handles various auth mechanisms for us. We'll be less explicit about why we're failing but we gain support for several authentication methods- swings and roundabouts!"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "No need to speficy attribute here. Moreover in yaml it is default to use lowercase names."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with System.Threading.Tasks.Task.",
      "reference": "In general I'm a trying to understand the reason behind this PR. Looks like if a blob (name) already exists we check if the contents are identical? In what scenarios this is not the case? When we want to publish a package/asset that has changed but still we want to use the same version?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the user agent.",
      "reference": "Can rename `req` to be `opener`, since that is the object, and it wraps `req` internally?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@MichaelDCurran, thoughts on adding a breakpoint format field attribute? It seems almost app specific, but I guess it does seem odd abusing line-prefix. Is there any more generic concept here?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `w3c` option.",
      "reference": "This would return a tuple of two dictionaries. You need to combine them and return a dictionary"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "What do you think of moving the example to the help text of the prompt? and the prompt itself can be \"What is your application's GitHub repository URL?\""
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Break out tests for events into their own tests rather than placing them in other ones. That makes it easier for us to figure out where problems lie and to do a TDD-driven implementation over new APIs."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Nice use of std::distance. I'm a bit worried about first += 9 though."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't this be `app.kubernetes.io/managed-by` as prometheus-operator manages this resource, but this resource isn't a part of prometheus-operator?"
    },
    {
      "prediction": "I don't think this is the case for the `InstrumentationName` tag.",
      "reference": "As long as we're being extra-vigilant about NREs, should we check that `httpMethod` and `requestUri` are not null?"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core/cli/ioctl/cmd.",
      "reference": "No need to have `xrc20` alias"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "the naming convention I'm been adopting if `_type` for instances of these classes. So maybe `context_config_type` is a better name for this fn"
    },
    {
      "prediction": "I don't think this is the right thing to do with this.",
      "reference": "Don't call it GPU mining, call it `externalMining`, here and throughout."
    },
    {
      "prediction": "I'm not sure if this is the right value for the 'media' resource.",
      "reference": "`within this with` typo, should be `within this width`"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `Prometheus.SpecAndStatus` instead of `Prometheus.SpecAndStatus` instead of `Prometheus.SpecAndStatus` instead of `Prometheus.SpecAndStatus` instead of `Prometheus.SpecAndStatus` instead of `Prometheus.SpecAndStatus` instead of `Prometheus.SpecAndStatus`",
      "reference": "how come this is false?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How about `Object.prototype.toString`? Or using the `typeof` operator?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I know @jzila suggested this, but I disagree: you're really not supposed to save a context in a struct. Can you get by with just saving the `Done()` channel instead? The `ctx` should continue to be passed around explicitly."
    },
    {
      "prediction": "I don't think this is the case for DNX451, but I think it's the case for DNX451.",
      "reference": "This check isn't right though."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "maybe `toolkitVersion` instead? It doesn't necessarily have to be called that in the generated code, but in the view model classes, I think it makes it clearer that it is the version of toolkit itself."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `opts.responseUrlFieldName`?",
      "reference": "the response data was added intentionally in #612, i think we could keep the `setFileState` stuff here as a special case, at least for now "
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This isn't really easy to read."
    },
    {
      "prediction": "I think this is a bug in CStorVolumeReplicaController.",
      "reference": "This line changed due to go formatting. Format was not there earlier."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The name \"Without\" in code is a little nebulous. Maybe something more descriptive like TrimPrefix or StripPrefix or WithoutPathPrefix or something like that. (Thoughts?)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "is this test in the move tests? I see what you mean then - it works, but I wonder if we won't lose track that it's being tested here."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I'm not sure if this wanted to be `json:\"tags\"` (which I'd set in my PR) or `json:\"tag\"` that someone elses PR had set. Given that the rest of the fields had their JSON field name set to the same as the struct field name, I opted for `tags`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "since the logic here and in `Proposal` is exactly the same, do you think it makes sense for us to include it elsewhere? I am not opposed to duplicated code when it makes sense, but the reason I first identified this was that I was looking for code in NCR::WorkOrder that was not specific to Work Orders. Seems like fiscal year logic might be helpful for reporting for other clients. In that case, we'd want this scope on those client data classes as well. Might be wrong to include this in the FiscalYear mixin, but it does seem like it should be outside of Proposal and WorkOrder. Does that make sense?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the connection.add_timeout(5, self.connect_to_rabbitmq) and self.connection.add_timeout(5, self.connect_to_rabbitmq) and self.connection.add_timeout(5, self.connect_to_rabbitmq) and self.connection.add_timeout(5, self.connect_to_rabbitmq)",
      "reference": "there is no static method as a go between -- how does this work?"
    },
    {
      "prediction": "I don't think it's a stringified symbol, but it's not a stringified symbol.",
      "reference": "Can you please change the name of this class to be something else?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we might prefer generalizing the interface rather than creating an exception. Current design of `h2o_next_token` assumes the input to be a comma-separated list, and allows the caller to specify a different separator when parsing a nested list. As I understand, what we are trying to attain in this PR is to have a way of parsing a flat list of semicolon-separated list. Assuming that is the case, I think it would be better to change the API of the function to accept two separators (i.e. inner and outer), where for our existing use-cases `outer` would be `,`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why not recycling? I Lru cache now recycling?"
    },
    {
      "prediction": "I don't think this is the case for the `PaymentVersionV2` and `PaymentVersionV3`.",
      "reference": "Why it is now called `PaymentVersionV3`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "changed for debug purpose?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the parent provider.",
      "reference": "@cijothomas I needed a way to set the Exporter.ParentProvider when the Processor's gets set. Internal to SDK though."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `from_motorway` flag?",
      "reference": "Talking through this scenario with @srividyacb and she's wondering if there should also be a check of `(from_trunk && node_based_graph.GetEdgeData(eid).flags.road_classification.IsLinkClass())` as highways with trunk classifications can also have this scenario."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "where does `master_certname` come from?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `make_res_layer` function. I'm not sure if this is the right thing to do with the `make_res_layer` function. I'm not sure if this is the right thing to do with the `make_res_layer` function.",
      "reference": "The line breaking is unnecessary."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why not enable split by space here ?"
    },
    {
      "prediction": "I think this is a bug in FPGA_INTEGRATED_DEVICEID and FPGA_DISCRETE_DEVICEID, but it's a bug in FPGA_INTEGRATED_DEVICEID.",
      "reference": "Shouldn't the operator be && ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "My best guess is that you want to use host.name in these parts to get the name of the host ?"
    },
    {
      "prediction": "I think this is a hack, but it seems that we don't want to do this for the root node type.",
      "reference": "IMO this edge case handling could remain here, just instead of overwriting the `n.nodeType`, the `makeEdgeType` method of `n` should be called, so `n.nodeType = nodeTypeEdge` -> `n.makeEdge()`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Just wondering... The two kinds of notifications are now quite different (Channel, text, maybe even icon). Would it make sense to extract the auto download notification to a new class instead of handling everything in the existing `notificationManager`? I have not checked if this will lead to a lot of code duplication, though."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Do we need to put this on the Call? We only need the API communication between the Encoding and the Transports which is currently done through the Transport.Request. The Call is used by users right?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "`ctx` is unused in GenerateAPIKey"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you judge the type of error?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Much simpler than a weird and confusing ``convolve`` call!"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Huh, this seems weird to me... Surely the suspenders render was called again in order to get the new `<div>Hello second 2</div>` output... Imma take a peak at these tests to understand what's going on"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Since this is just a helper function to create text, perhaps this could live in a helper? I noticed that we have a few other error/message creators in the application controller as well, but I think this type of function should be re-factored to be part of a helper."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Will this mess up parsing the messages by other editors? (vscode, vim ...)"
    },
    {
      "prediction": "I don't think we want to use `File.expand_path('../Gemfile', __dir__)`, but we want to use `File.expand_path('../Gemfile', __dir__)`, but we want to use `File.expand_path('../Gemfile', __dir__)`, but we want to use `File.expand_path('../Gemfile', __dir__)`, but we want to use `File",
      "reference": "Style/StringLiterals: Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "Why can the pool be null?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "It might be good to have a note here: > work-around for issue #7562 allowing us to differentiate presentational lists from interactive lists (such as of size greater 1 and ARIA list boxes). In firefox, this is possible by the presence of a read-only state, even in content editable."
    },
    {
      "prediction": "I don't think that the data of the node (or the node itself).",
      "reference": "This set of changes is the one part of this that I'm not completely sure is valid. Can someone look over this to make sure I got the E's right?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "There doesn't seem to be a reason to copy this here."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We've avoided including h2o headers in BPF programs because it's a runtime dependency. However, IIRC, this is because h2olog was maintained in the separate repository so that h2olog did not know where h2o was installed. Now h2olog can use `H2O_ROOT`, we should add it to BCC's `cflags` in order to include h2o headers in BPF programs."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think the docstring here should include the CLI arg `--alert.query-url` just to make it clear to users which setting this uses."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Same change just above?"
    },
    {
      "prediction": "I think this should be a test for `n` and `\u043b` for `n` and `\u043b` for `n` and `\u043b` for `n` and `\u043b` for `n` and `\u043b` for `n` and `\u043b` for `n`",
      "reference": "Could you check the result content rather than just the number of search results please? For example with this test if the search engine suddenly starts returning \"latin n\" for both queries, we won't know about it."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: I think that `workloadID` should suffice for this test... that's what we'd be issuing anyways"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should have a rule to detect identical catch branches"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "remove these from the targets file."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `github.com/ethersphere/bee/pkg/p2p/protobuf` or `github.com/ethersphere/bee/pkg/p2p/protobuf`?",
      "reference": "now that we have the signature in the hive messages, it might be that this must be drastically reduced, since there are limits on the protobuf reader/writers i believe"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I recommend that we move this to be optional, as other users might not need it. Can you look at `OPTIONAL_PACKAGES` section, around line 68?"
    },
    {
      "prediction": "I don't think this is a bug in javaslang.control.",
      "reference": "I usually set idea to never use wildcard import such as `import java.util.*;` Now i use setting from javaslang standard."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Where is host['ips'] coming from?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "oh! missed a `:` here; let me fix that; also can get rid of the intermediate variable"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `with_parallel_approvers` and `with_parallel_approvers.first.update(first_name: \"Uniquely\", last_name: \"Named\")` and `with_parallel_approvers.second.update(first_name: \"Onlyof\", last_name: \"Itskind\")`",
      "reference": "Is this necessary?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `i18n` module, but I'm not sure if this is the right thing to do with the `i18n` module.",
      "reference": "I'd create a different method for each render section."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Instead of storing the revert flag in the tracer is it possible to use org.hyperledger.besu.ethereum.mainnet.TransactionProcessor.Result#getRevertReason? (via org.hyperledger.besu.ethereum.transaction.TransactionSimulatorResult#getResult)? If a TX reverts without a reason do we get an empty revert reason or a revert reason with zero bytes?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the right thing to do.",
      "reference": "I think this should test with and without container reuse if that is implemented in this PR. Probably just make this test parameterized."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "These modifications allow BaseFile to translate into a SparkRow with the specID as a column"
    },
    {
      "prediction": "This is a hack.",
      "reference": "is this something we've been missing this whole time?"
    },
    {
      "prediction": "I'm not sure why this is a good idea.",
      "reference": "nit: this is a package-wide constant so better to narrow the scope like `allEventsSign`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There seems to be some repetition. Does a local function make this code shorter overall?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Might be cheaper to reuse the `null` assignment of line 313 and set `isHydrating` to null instead WDYT?"
    },
    {
      "prediction": "I'm not sure if this is a class, but I'm not sure if this is a class, but I'm not sure if this is a class.",
      "reference": "Revert this blank line"
    },
    {
      "prediction": "Should we remove this?",
      "reference": "This was introduced recently for the Hadoop 3 upgrade. Copy/paste error but definitely causing some of the new test failures."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `before_action` and `before_action` and `before_action` parameters.",
      "reference": "I think we should only need to do this for `:approve` since we are using `authenticate_user!` for all other actions and that checks for disabled client"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I wonder if we should create new tests for header checks; here for instance we're mixing querystring and headers. Thoughts?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `apply_helpers::custom_facts`?",
      "reference": "We should be able to add sensitive by hard-coding the parameters, same as you put into the metadata in apply_helpers."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do you think that it is necessary to create this class?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "replacing the `1` with `io.SeekCurrent` may be good here"
    },
    {
      "prediction": "I think this is a bug in the go-jose.v2 package.",
      "reference": "nit: perhaps this file would be better named `jwks_source.go` ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "It will be helpful to specify the intended priority as well for the properties within this file."
    },
    {
      "prediction": "I don't think this is a good idea to use `exec.Cmd` instead of `exec.Cmd`?",
      "reference": "Make this private and update all the public functions to not take this argument. The variable you set below should also be private, then in the tests instead of passing the variable in to the function just update the variable. We don't want to expose the testing implementation in the public api if it can be avoided."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `hive/tpcds/customer/customer.dat`?",
      "reference": "Do you now why is it a specific table name is used as a default?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "If all you're doing is checking for the existence of a directory as your \"temp\" directory, why does it matter what OS you're on?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "nit- would be cleaner to import it once"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Looks like there is a closing parenthesis `)` missing here."
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "this one bothers me. There are many places where this one is written to for an error message and just a single callsite is changed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You can put this in `kbfsOpsInit()` in you want, so we don't have to call it in every test."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`ARM_32` is what clients define as an input to DR, and is not always defined internally: we use just `ARM` to mean AArch32."
    },
    {
      "prediction": "This is a hack.",
      "reference": "s/for use/to use for/"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "` $event->getAvatarFilename()` this function return `string` or `null`. In this place ` $event->getAvatarFilename()->getValue()` return `Fatal error `"
    },
    {
      "prediction": "I don't think it's a problem here.",
      "reference": "why not creating a new error type for server's own resource limit exceed error and do conversion within rpc interceptor?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could be a timing thing here. When options are created they'll copy the ref for the current default propagator. If user sets through SDK the global propagator after that, it won't be reflected. Could leave it null here and then when it is used in instrumentation do `options.Propagator ?? Propagators.DefaultTextMapPropagator`. It would be a slight perf hit but it makes it hot-swappable."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Unrelated file. Please remove from PR."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Careful: you only want two newlines after the final header message. (That indicates the end of headers and the start of data.)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This will not work on Python 3 (to which we are transitioning) because `.content` is bytes, not a str. Can you make the pattern a bytes object as well (like so: `b\"pattern\"`)?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `aria-expanded` attribute.",
      "reference": "This was to allow the tests to pass when the order of the required was different. Silly, but we don't have an easy way to check for \"equal but order doesn't matter\" in chai."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "maybe say \"returns the default cost method that returns an object of cost 1\"."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I believe these rules will be enforced both (1) on egress from a local workload, and (2) on ingress **to** a local workload. Right? I understand that we definitely want (1), but do we really want to enforce (2) as well?"
    },
    {
      "prediction": "I think this should be a JSON object, but it's not a JSON object.",
      "reference": "Use `response.asJsonObject()` instead. Also, use `put()` instead of `putOpt()`, `null` as a value is fine."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Are you sure? We've changed it during an introduction of the IME support."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I think here we want the use of `empty()` to take care of empty strings. If you put `dql_filter: ''` in your YAML config ... this will add `->andWhere('')` and it will fail, right?"
    },
    {
      "prediction": "I think this is a bug in p2p.GetBroadcastMsg.",
      "reference": "this is golang's named return, err is defined, `return` is equivalent to `return err` the current code has no problem"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `output_buffer` argument.",
      "reference": "I don't think this is right; in Rust terms it's like a `&mut String`, in Java `StringBuilder` - it's not a return value from the function which is what `(out)` is for."
    },
    {
      "prediction": "I don't think this is a problem. I don't think this is a problem.",
      "reference": "If the label is not binary, should we rename this function?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "This is very-very bad idea because of its performance impact"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "WHY U NOT SORT IMPORTS?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `sign_in_as` method.",
      "reference": "Put a comma after the last item of a multiline hash."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "How come we need ``Dimensioned`` in the top-level namespace?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "excess whitespace through plugin."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "What is the problem here? I feel we used this in a lot of places."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Update the docstring."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `require` or `testify/require.js`?",
      "reference": "delete the empty line \"github.com/pkg/errors\" should be grouped with other third party packages same for the rest"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Assigning capabilities to the field here is not the best idea. Semantically this field contains the capabilities returned by the browser after session start. So here we sould better amend capabilities and return them from `init` method to pass later to `startSession` method (that will assign the capabilities returned by the browser to the field)."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with RSpec::Core::Time.now?",
      "reference": "Is this a breaking change, or is the API private?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't think we need this dependency in this project right now"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I don't think this is necessary since `CommonLabels` is a public func and every component name is also public constant."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `puppet`?",
      "reference": "The `_example` field should be updated to include an interpreter with an array value."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Put this in the godoc of SupportedProtocols instead. Preferably we would just use one map though. Why not just use this one?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd feel a little safer if the first argument were a string, not a *string unless there's a particular reason for making it a pointer."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Can you please revert changes to files in the `thoughtworks` package? This is legacy code and we will eventually phase out RC."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You can safely revert changes to this file."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This deletion is unnecessary."
    },
    {
      "prediction": "I think this should be a string, but it's not a string.",
      "reference": "I'm not a huge fan of this overloading of the prop; accepting very different types of arguments for props like this can be confusing, and wasn't part of the IB. I understand wanting to import the SVG directly, but the IB suggests using `${global._googlesitekitLegacyData.admin.assetsRoot}${userInputSuccessImage}` as the `src`/`smallImage` value here. It'd be great to refactor this to accept components directly in the future, but let's do that all-at-once rather than this hybrid approach that makes the API less clear."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I've had this happen recently with IntelliJ, was this intentional?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Order(1) vs Order(logN) -- not sure it's measurable at the ~200 element size of the table. All of the published comparisons start at ~1000 elements."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I don't know about this aliasing and 'factory'. Previous version was rather straightforward: `location.CreateLocationResolver`. Perhaps `location.CreateResolver` would be even better? What do we actually gain here from moving DI to a separate sub-package?"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Use `UpperCamelCase` for function names"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `Date.parse(value)` instead of `Date.parse(value)` instead of `Date.parse(value)` and `Date.parse(value)` instead of `Date.parse(value)` and `Date.parse(value)` instead of `Date.parse(value)`",
      "reference": "I'm not 100% sold on this idea but I like it in general. Nice compromise between using the 'Date' constructor where possible and falling back to the pre #5880 behavior when it makes sense. However, instead of `Number(value) < 0`, let's do `Number(value) < MIN_YEAR` because `new Date('-2017')` is perfectly valid in JS and I don't want to break the date behavior."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Remember to close SOLR-11877 after this"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this change should be reverted"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This function signature is a bit complicated, some parameters are IN type (stopLoop which is modified from outside), others are OUT (registeredEvent channel which is modified inside function) I suggest the following signature -> SubscribeToRegistrationEvent(identityAddress) returns registeredEvent chan of type (RegisteredEvent not int), Unsubscribe func(), error (in case of any error). That way caller can always cance subscription if needed and check for any errors. Also - unsubscribe function hides any internal details how subscribtion is really implemented"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `copy` or `injectBundle`?",
      "reference": "`.wav`?! cannot we use something slightly more modern and compressed instead? :) I dunno, like `.mp3` or `.aac` or `.ogg`..."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Wouldn't a single signal call be enough? (without the boolean even)"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "I suspect that this whole block, which is going to be repeated a number of times, should probably be in a helper. I guess it would need to be given the object and the title and could probably figure out everything else from that?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Should we expose this attribute in the Asciidoctor.js API ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think contains on `Multimap` was broken - it should return true if one of the values is associated with the key? It that right"
    },
    {
      "prediction": "I think this is the default value for the default value for the default value for the default value for the default value for the default value.",
      "reference": "delete this line"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Presumably we no longer need `force: true` here."
    },
    {
      "prediction": "I think this is a bit of a hack, but I think it's a bit of a hack, but I think it's a bit of a hack, but I think it's a bit of a hack, but I think it's a bit of a hack.",
      "reference": "HIP runtime is compiled using a C++ compiler. So comparison to both NULL as well as 0 does not make sense. Just comparing to NULL is sufficient."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `help_url` and `feedback_url`?",
      "reference": "these urls are still in `a` tags so we should probably include these links separately for a non-HTML version"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "That's fine though, meaning that you can send to this channel under the server lock. The internalSendLoop will pick up the change when the server lock is released (if loop is blocked trying to grab the server lock). Even the way you do it here (releasing the lock, sending, then reacquiring) does not guarantee that the internalSendLoop will have time to refresh in that interval."
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's a string, but it's not a string.",
      "reference": "The name `enableDownloading` implies this is a boolean capability. How about `downloadDir`?"
    },
    {
      "prediction": "I think this is the default validator.",
      "reference": "Found one internal team is using this method. Will coordinate with them about the migration solution."
    },
    {
      "prediction": "I think this is a bug in Datadog.",
      "reference": "The field `HttpServerErrorCodes` should be called `HttpServerErrorStatuses`"
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "Can you please make each of these in a separate line. It will be easier to keep them sorted, and add/remove."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `allowOverwrite` parameter?",
      "reference": "should we error instead of silently ignoring the `cleanup` param? it defaults to `false`, so someone must have explicitly set it to `true`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There is no specific requirement that the root be called `root`, just that there is a single root directory and that it be the first entry in the zip."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "perhaps we should encapsulate this logic in a helper method w a test?"
    },
    {
      "prediction": "I don't think this is a problem with the `beaker/options` module.",
      "reference": "Now that we're only using this repo as a Gem you shouldn't need to `require` an expanded local file path like below."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but I'm not sure if this is the case.",
      "reference": "This isn't necessarily a year. It may be months, days, or hours. Can we return `intValue()` directly instead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is redundant because it gets logged immediately on entering the handleContainerChange function"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`ds.GenericDeploymentConfig.DeploymentNotification` in L128 is nullable."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this shouldn't be exposed here - this class isn't a carriage for this - its used internally to determine if/how we can mine."
    },
    {
      "prediction": "I'm not sure if this is a bug in Firefox.",
      "reference": "It's fine to leave these checks in. It'll make the exception come from `FirefoxDriver`, and that's probably clearer to a user."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "We don't want to include the `IntegrationSpecHelper` for models...mind moving this line out of the loop to be `config.include EnvironmentSpecHelper, type: :model`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please check the return on these."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `cache` option.",
      "reference": "Do we need `==` for true?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Changing the default value may cause BC-breaking. Suggest changing this value in config."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "how does that happen?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This is gross/clever. :-)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Take a look at the name of this file. Definitely copy and  "
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Can you check with @mahebbar how to work this error. Should be different from 404."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do we still need the upper bound `<3.9`?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Does this mean `vendor/bin/psalm` is not a symlink (or whatever equivalent Windows has for symlinks) on Windows?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@lpabon having a separate package name `aws_test` allows to test the package as if the tester was an external package. If the test package name is the same as the package being tested, the test package can also use methods and variables not exposed to the eventual user."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The exporter should still be able to test these histogram instrument kinds, right? Is there another reason to remove these?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should this increment eval.Round somehow?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Although this change looks good. Maybe there are other inconsistent cases too?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "This is a way better method name."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Prefer single-quoted strings when you don't need string interpolation or special symbols."
    },
    {
      "prediction": "I'm not sure if this is a valid option?",
      "reference": "I was wondering if this should allow per role specification, instead of (or in addition to) a generic \"allowed everywhere\". So you could do: `{ separator: ['aria-valuenow', 'aria-valuemin', 'aria-valuemax'] }`. You could still allow the array, and you could add a wildcard option for the \"generic\" case you've got now: `{ '*': ['always-allowed'] }`."
    },
    {
      "prediction": "I think this is a bug in NABasicObject.",
      "reference": "I'm confused by the name. The string was a Hive string but it isn't any longer? Why should we care? (I imagine I'll find the answer later... there is some different semantic that we want downstream...)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Could you please leave the explicit imports?"
    },
    {
      "prediction": "I'm not sure why this is a bug in iotex-core.",
      "reference": "Why need alias?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Shouldn't this be a `libfs.nullIDGetter` (exported, of course)?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "I dislike the messages.go pattern; the strings are only used once and make more sense in context. The other two added reportErrorf() calls in clerk.go have inline strings."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Seems we don't need it anymore."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This might cause problems with the weird way we publish Guidance and Groups in the UI. We will have to make sure that UAT is thorough."
    },
    {
      "prediction": "I think this should be a function that returns an error instead of an error.",
      "reference": "this default needs to be on order 1 minute, I'm not sure why we defaulted to 1 hour below..."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I figure to make `{env.*}` work, right? I can't think of any other placeholder that makes sense here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why change the port from 0 to getAvailablePort()?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "For me would be great don't repeat timeout sending in every get_locator call. Looks like it should be sent into LocatorsManager init. And possibly it should me non mandatory, something like that: `def __init__ (self, locators, timeout=60):`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I feel like since now we don't initiate the `opts.projectName` with `opts.ProjectName()`, which means `opts.projectName` and `opts.ProjectName()` they don't necessarily equal to each other, we need to also substitute all usage of `opts.ProjectName()` within `Ask()`, `Validate()`, and `Execute()` to `opts.projectName`. Otherwise if `-p` is set, `opts.ProjectName()` will get expired."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why do we thinkg that an empty string is ok to return from this method? I think the null should never be passed in here in the first place"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: can remove this `else` since we return from the condition above."
    },
    {
      "prediction": "I don't think this should be used in the future.",
      "reference": "You missed `Write<T>(...)`! I'm kidding ofc."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Was there a customer who had this set to an empty string?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I know we have the `reporter` spec below, but what about a unit test for this to explain reasoning behind logic? If I were going to update this decorator, I would assume it wasn't covered by tests because there is no unit test."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "it's better to be : void attach(String name, Part part);"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "I didn't see where the IOException can get thrown, is this just to match the V1 reader?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We normally suppress this warning with `RDUSED_PARAM(forceRDKit)`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "What if `Game::getPlayerByNameWildcard` had not been called before. It would not find a player, wouldn't it?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Why upper case \"R\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this need to return an error or could it return `false, nil`?"
    },
    {
      "prediction": "I'm not sure if this is a thread-safe method, but I'm not sure if this is a thread-safe method. I'm not sure if this is a thread-safe method. I'm not sure if this is a thread-safe method. I'm not sure if this is a thread-safe method. I'm not sure if this is a thread-safe method. I'm not sure if this is a thread-safe method.",
      "reference": "Can you not change those scopes in public API classes? This applies here and in other places -- protected changed to package-scope for source is not really an API-compatible change."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "this parameter is only used in POST, please use `getRequest()->request->get('...');` Thanks"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Problem number 1: Scoped packages would have a `/` character here. Changing this to `validatePackage` resolves the 403."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't quite get why there would be key errors: ``deep_mapped`` is a clone of ``self`` and ``k`` comes from ``self.items()`` so why would the key ever be rejected?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this chain ID determines only from which chain to withdraw, therefore your changes do not accomplish what you want them to accomplish. You'll need changes to `func (aps *hermesPromiseSettler) Withdraw(chainID int64, providerID identity.Identity, hermesID, beneficiary common.Address) error`. The method probably has to include two chain ids: to and from. Currently, the method internally uses: `aps.config.L1ChainID` -> the chain to withdraw to `chainID` -> the chainID that was passed as the chain that the withdrawal is originating from."
    },
    {
      "prediction": "I think this is a bug in the future. I think this is a bug in the future.",
      "reference": "If instead we had `TraceContext.extract` return a bool value as a second return value, we could avoid the byte array comparison in `TraceID.IsValid`. Did you consider that alternative?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "here shouldn't we use `depotFreeLimit`?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Could we use the Rails application's secret token instead? Do we actually need our own here?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "so should be fixed here also"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I would just remove this assert as it's going to get un-maintainable with a long list of valid sizes. Ditto below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`HostDataDir` is misleading. Can we rename it to something more relevant ? The constant should also be moved up and reused as necessary."
    },
    {
      "prediction": "I don't think this is the default.",
      "reference": "I still feel like we are double-counting the outer IP header here (once in `defaultMTUGRE` and once in `ipsecESPOverhead`) but I'm not that familiar with IPsec."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `MeasurementProcessor<MeasurementItem>.OnEnd<T>` method.",
      "reference": "Not sure what benefit we gain by extending BaseProcessor here, as this seems to be defining a new OnEnd method. Could we modify MeasurementItem to have all the things, and then MeasurementProcessor can be simply extending BaseProcessor<MeasurementItem> (not blocking. just noting some observations in the PR :) )"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This change was not really intended but made by the linter of VS Code. And looking at other packages this looks like a best practise to place interal packages on the top and gh imports afterwards."
    },
    {
      "prediction": "I don't think this is the default sampling policy.",
      "reference": "This seems like a more appropriate message under `ListenAndServe`. WDYT?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Is this not required?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We should start thinking of an object that encapsulates this information :) we might need more arguments in the future."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Given that we are (conceptually) searching across multiple self-dependencies, all we can say is that we didn't have a self dependency in which *both* source and dest masks were correct. Since the spec doesn't imagine this case, the valid usage statement assume we can differentiate only wrong source from only wrong dest within a *single* self-dependency -- which we can't across multiple (at least not meaningfully)... so we always return both the source/dest VUID's if we can't find a self-dependency in with *both* are correct."
    },
    {
      "prediction": "I think this should be the same as the `isMining` method.",
      "reference": "rename? MiningCoordinator always exists"
    },
    {
      "prediction": "I don't know how to use `pluginManager.getConfig(\"api\").offline_mode` or `pluginManager.getConfig(\"api\").offline_mode`?",
      "reference": "Here would be the same case you don't need to call `loadConfigs`, but you would need to reread configs using `getConfig` on each getHost function call, not once per file."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Unlocking with defer means that this lock is still held curing the call to forgetNode(), below, which I see attempts to acquire `f.mu`, which looks dangerous to me."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does anyone still use the cst out of this method? If not consider deleting"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Line is too long. [97/80]"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This seems unused."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "@luguanglong , Thanks for the fix, can you re-phrase it to sound better something like \"This OS version is currently un-supported by keadm\""
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "should probably be called `_DeleteFpInfoAttr` because it removes it. Cleaning gives the impression it is still there. I would also move this to the end of the function `GetAtomicWeightsForFingerprint`."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `std::make_pair(VK_PIPELINE_BIND_POINT_GRAPHICS, \"VUID-vkCmdBindDescriptorSets-pipelineBindPoint-00361\"), but it's not a good idea to use `std::make_pair(VK_PIPELINE_BIND_POINT_COMPUTE, \"VUID-vkCmdBindDescriptorSets-pipelineBindPoint-",
      "reference": "nit, can we use `VK_PIPELINE_BIND_POINT_RAY_TRACING_KHR` here (granted it isn't else where, maybe worth fixing here or in separate PR)"
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "This will need to be updated in the upcase-exercises repo as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Think it's worth extracting this to `Exercise#complete?`?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "This is still a potentially useful public method - should we remove such methods?"
    },
    {
      "prediction": "I don't think this is the default.",
      "reference": "I don't understand this change, what is happening here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think its worth stating this is `versionMajor`"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "rebuild: say loads and merges"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Why was this removed here (also in the other file)? Shouldn't we import them so that the reference in the docs below is interpreted correctly?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I'd prefer to have a blank line between the class declaration and its first member. Is it possible?"
    },
    {
      "prediction": "I don't think this is the default value, but it's not the default value, but it's not the default value, but it's the default value.",
      "reference": "Is it really LEGACY_HELLO if we are using the most up to date HELLO? Perhaps `MONGOS_HELLO` would work here?"
    },
    {
      "prediction": "Should we ignore the error here?",
      "reference": "I am afraid this is going to cause problems on Windows where it is not uncommon to have injected threads (CTRL_SHUTDOWN, CTRL_LOGOFF, etc.) we have no privileges to suspend -- and thus retrying will just fail again, and with the new \"synchall failure is fatal and should kill the process\" approach it turns what used to work for us on Windows into process death."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `--mac_signing_identifier <id>', 'The identifier to use for signing the installer', 'login')",
      "reference": "think it should only be in create_dist"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Do you plan to support Pod spec change? Like hostPort is added/removed later after Pod creation?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Is this behavior correct? It used to return `true`, which should map to `dokan.ExistingDir`. Was that previously a bug?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What about just printing an empty list in this case? That would make the output more predictable."
    },
    {
      "prediction": "I'm not sure if this.container.querySelector('.gh-editor-container')[0].querySelector('.gh-editor-container')[0].querySelector('.gh-editor-container')[0].querySelector('.gh-editor-container')[0].querySelector('.gh-editor-container')[0].querySelector('.gh-editor-container')[0].querySelector('.gh-editor-container')[",
      "reference": "I looked and couldn't find any usage of `container` in any of the editor component files (js or hbs), so I assume this was used once and didn't get removed?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "I just updated a number of sites using older versions of Roots onto WP 3.6 and this little function change was required. Multiple search bars were displaying when I used the search widget in a widgetized sidebar. Updated the roots_get_search_form as seen in this change resolved it for me!"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Fixes test failed in some cases"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "what's the prod url for this? just curious. @amirsaber"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can you please change this to azkaban.jobs.java.opts?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `googlesitekit-module-analytics` class, but it's not the right thing to do with the `googlesitekit-module-analytics` class.",
      "reference": "Here is another concatenation which should be updated. Even though `Source:` and the link are essentially separate, it isn't RTL friendly. This would be another good use for `createInterpolateElement` I think so that we wouldn't need to include all of the classnames in the translation string (or extract them to a placeholder). That would allow us to use the `Link` component as well, rather than using its resulting HTML as a string which will be a pain to maintain if we were to make changes to the base `Link` component."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I would add an overload `GetCancelledZeroTask()` which calls `GetCancelledZeroTask(CancellationToken.None)`. This is cleaner than requiring the caller to pass `default(CancellationToken)` or `CancellationToken.None`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would it be equivalent to check if `chain != nullptr` below? Not suggesting a change, just curious."
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "Should probably do `auto this_l (shared_from_this ());` and pass/use that instead of `this`. Same a few other places. IOW, replace both `shared_from_this()` and `this` with `this_l`"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "And here. Please, use `'` for apostrophes in changed strings in this file."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "assignments should only be cuddled with other assignments (from `wsl`)"
    },
    {
      "prediction": "I don't think this is the default data version for new blocks.",
      "reference": "Please move this to `block_types.go`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with NLog.Layouts and NLog.Layouts.",
      "reference": "So this is not needed anymore for all attributes?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Happy to get suggestion for better messaging here. Here's what I intended to convey: Something is wrong - the Exception is a hint to what might be the cause The impact of that - tracing wont work."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I think we can remove this function, right? (duplicate with `ses_starter.py`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "With this fix, I am not even sure we need to overwrite this function."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Why not just import this from `data_transfer`? As a rule copying the same code twice is not a good idea. Also: please run `pylint` on all files in this PR."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "You've got an absolute path here referencing your home dir :-)."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `prefix` and `postfix` properties.",
      "reference": "Maybe I should do some sorting so that these properties don't keep moving around..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we keep this test anyway, as it's part of the spec?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can be removed"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It's a minor quibble I know, but I like having the imports ordered by lengt"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It's better to get the charset from context or other setting to let the user override it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this filename as well needs change"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `json:\"accessKeyID` and `json:\"secretAccessKeySecretRef` and `json:\"hostedZoneID\"`",
      "reference": "I think we want to remove `omitempty` here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You cannot move this here because it breaks detach. Just call `tty.Close()` before returning the error from start"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "I updated only the implicit roles who needed a update for this new rule to validate."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `protoreflect` and `protoreflect` package.",
      "reference": "> // Code generated by protoc-gen-go. DO NOT EDIT."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "minor: skipOSConfigMetadata, otherwise, the name sounds like a boolean"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "~~I think lines 65-67 should be moved into this else clause after `type = ...` Else, it is a bit confusing why we check the enclose type validity a second time~~ Nevermind, will do some refactoring, myself. But thanks for \"fixing\" this!"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`sessions := endpoints.SessionsDTO{}` and using only `sessions` should be simpler."
    },
    {
      "prediction": "This is a hack.",
      "reference": "These need to be in the other order to avoid crashing when dcontext == GLOBAL_DCONTEXT (==-1)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not change the other samples?"
    },
    {
      "prediction": "I'm not sure if this is a header?",
      "reference": "Indentation is mixed up here due to spaces/tabs, I'm guessing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we provide a little more context in the error message? Maybe throw in something about what operation was being performed?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Project standard is spaces, not tabs. Please fix and then we can merge this."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "@hgtw is there anything we're worried about with regards to using this cache? Do we want to do staged testing around expeditions before we merge? Curious your thoughts here"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The purpose of this was to allow pushing filters into the manifest files if we ever use a format other than Parquet. I think overall this is a good change because we can add it back later. Just wanted to note why the unused argument was there."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "I think BSON::Decimal128 should always be serialized as Decimal128 regardless of config option."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `bolt_spec/files.rb` or `bolt_spec/files.rb`?",
      "reference": "We should probably just move the `require 'bolt/plan_creator'` in `Bolt::CLI` to `Bolt::Application` so it will already be loaded."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the default job.",
      "reference": ">20 [](start = 45, length = 2) Can we override this at runtime? Maybe it should be a command line option with default."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `env` property.",
      "reference": "can just remove it ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Better call it `CleanUpMirrorInfo`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@shannonwells is there still something missing here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This could be more indicative of what it is... e.g... `stresstest_time_limit`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Shouldn't we do a `reader_payload_pool_.reset()` here?"
    },
    {
      "prediction": "I'm not sure if this block's author leader is the same as this block's author leader.",
      "reference": "I'd prefer the nomenclature less tightly coupled to DRAND throughout. I played with renaming the `drand` package to `beacon` but it was too much noise in this change."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `_current_key` method.",
      "reference": "I think I would prefer you declare `self._current_key=None` in the constructor and just return `self._current_key`. That way you can prevent anyone from overwriting `current_key` without needing to use `getattr` here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I guess I like the name `mode` okay. I can't think of anything better."
    },
    {
      "prediction": "I think this is the default timeout.",
      "reference": "I would create a new method (NewStepWithDefaultTimeout?) for this purpose because timeout<=0 looks like a hidden logic"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are these limit changes related?"
    },
    {
      "prediction": "I don't think this is a bug in scapy.utils6.",
      "reference": "Don't you mean `import scapy.consts`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`ctx` is unused in rollbackPrimary"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "This is not what title says."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "a fix applies several fixes? maybe this should simply be `applyToNode`"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "U1000: func `fakeGetOk` is unused (from `unused`)"
    },
    {
      "prediction": "I don't think this is a bug in the go-multierror package.",
      "reference": "Because there is a \"k8s.io/client-go/tools/cache\" below, we can sort out all the \"imports\" here."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Nit should be using `goimports` to format the import statements with standard libary imports first, new line, followed by non-standard library imports."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Do we not have tests for pipeline delete  "
    },
    {
      "prediction": "I think this should be removed in 2.3.0",
      "reference": "Good that you mention this constraint in the docstring :)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `k8s.io/apimachinery/pkg/api/errors`",
      "reference": "remove this blank?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Partitions is misspelled 8 times in this commit, might make sense to fix the spelling for all of those."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with QProcessEnvironment.",
      "reference": "Please remove this blank line - those are only used to group Python/third-party/qutebrowser imports."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "`insecure` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Same as above (HTTP in upper-case)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This is getting repetitive  maybe you could introduce an abstract test case with a `getExpectedUrl($providerReference)` method ?"
    },
    {
      "prediction": "I think this is a bug in Go.",
      "reference": "I do not think returning `Value{}` is correct here. For example, `reflect.MakeFunc(...).Kind()` would return `reflect.Invalid` instead of `reflect.Func`. Therefore, I think this should panic instead."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Does this work for Custom Elements? iirc we're lacking test cases for them. /cc @andrewiggins @developit"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Same change just above?"
    },
    {
      "prediction": "I think this is a bug in WebOS 2.0.",
      "reference": "I suppose `apploader.js` isn't used by WebWorkers. So `self` will always be `window` here."
    },
    {
      "prediction": "I don't think we want to use `ssh_nodes` instead of `skip_targets`.",
      "reference": "Since this var is no longer defined we should remove the `if skip_targets.any?` bit below."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think we should `return arn` as a fallback at the end of this function (otherwise the `['Resource']` entry below could become `None`)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why session is started at all, if you need to shut it down e.g. DI should launch noopSession"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: can we rename the interface to `wsFileDeleter`"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Why target cannot be external endpoints?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We use a suffix \".AUTOCREATED\" for configsets, maybe we can use the same here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This one won't be disposed. Should be (something like) `using var openTelemetry = OpenTelemetrySdk.EnableOpenTelemetry(` no?"
    },
    {
      "prediction": "I'm not sure why this is necessary?",
      "reference": "Why this is in the diff?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "How is status determined? When the user calls CloudBackupCreate( src_volume_id ) they can then call CloudBackupStatus( src_volume_id ) Is there something similar for this new API?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "We could pass `excessDomChildren` to `options._catchError` and only do this if an error-boundary catches the error. Not entirely sure if that's better."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `setHash` method.",
      "reference": "In php8 named parameters were introduced and now it is required to match called method parameter name when setting parameters by array destructing or call_user_func_array() etc."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "If instead we had `B3.extractSingleHeader` and `B3.extract` return a bool value as a second return value, we could avoid the byte array comparison in `TraceID.IsValid`. Did you consider that alternative?"
    },
    {
      "prediction": "How to do this?",
      "reference": "I think this is more of a semantic difference than a typo - `weiter hinzufgen` is like `continue adding` whereas `weitere hinzufgen` is like `add more`. I think it makes sense to change it though  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: 200 is superfluous"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is testing `unreserved keyword`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "paramsNatOrigin doesn't include sUVtoST. I would just remove that definition for now"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It feels like the test should be waiting for the prefetcher to shut down, but I don't have a great reason why other than that it might be confusing for debugging if there are still goroutines from old prefetchers lying. But I guess since `TogglePrefetcher(false)` doesn't actually set the prefetcher to nil, the queue shutdown method will still end up waiting for the shutdown to finish. If that sounds right, nevermind me."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "As a long term thing, would it make sense to move the resource names as keys under the requirements map?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "That doesn't fix the whole problem. The issue lays in this line right here, not the one above. There are two problems with this line: 1. It finds things that aren't cells in the table 2. if it doesn't find anything, it shouldn't return empty here, but continue down to look for row/ column headers."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I am pretty sure that this is infinite recursion as getAllProjects returns the project itself."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Something I didn't catch before I merged this PR, is the hyphenated constant a problem? E.g. should \"data-lists\" be \"data_lists\"? @paulkaplan"
    },
    {
      "prediction": "I don't think this is a problem with the wpcap.dll?",
      "reference": "Can you write the test as `if not (conf.use_winpcapy or conf.use_pcap or conf.use_dnet):`"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "we have to include foreign assets on the repository directly because they don't belong to a job? This seems very awkward... Is this a step towards the job-less assets on the repository? Did you consider having `build_asset_job` take in a set of foreign assets instead? I suppose we would then need to subclass it to be a more special `AssetJobDefinition` that can keep track of them."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "`-Wstringop-truncation` is a new kind of error detector introduced in GCC 8. As for this patch, these are two false-positives though."
    },
    {
      "prediction": "I don't think this is a problem with the `source_profile` and `credential_source` section.",
      "reference": "Can we port this error msg to v2 too? This one is better, as it explicitly states what sources are allowed."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The convention so far has been to require directly from the defining file (in this case `../../read_preference') . I think the concern has been mostly about the potential for circular dependency cycles"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I suggest expanding dims here to simplify the formatting."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with kinto.ini.",
      "reference": "Why do you need to specify the kinto prefix here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The `!r` is unnecessary."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I didn't see existing tests for this `OpenBucketURL`. Not sure if it's easy to do without mocking these `opener` calls."
    },
    {
      "prediction": "I'm not sure if this is a template model. I'm not sure if this is a template model. I'm not sure if this is a template model. I'm not sure if this is a template model. I'm not sure if this is a template model. I'm not sure if this is a template model. I'm not sure if this is a template model. I'm not sure if this is a template model. I'm not sure if this is a template model.",
      "reference": "Should we default to `true` ?"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `babel-preset-react` instead of `babel-preset-react` instead of `babel-preset-react` instead of `babel-preset-react`.",
      "reference": "Shouldn't these options also include `@babel/preset-env`? Also I see you set `babelrc` to `false`, could we rely on our existing `.babelrc` file? Feels like some duplicate configuration otherwise."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: We can use `%s` since `disconnectReason` is a string."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I think it's better to create a new example"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The stages are correct, but the more forgiving `kAttachmentRasterOrder` should be used, based on a review of the spec. That should give the same effect of suppressing the false positive conflict between the DEPTH R/W and resolve. > End-of-subpass multisample resolves are treated as color attachment writes for the purposes of synchronization. This applies to resolve operations for both color and depth/stencil attachments. That is, they are considered to execute in the VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT pipeline stage and their writes are synchronized with VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT. Synchronization between rendering within a subpass and any resolve operations at the end of the subpass occurs automatically, without need for explicit dependencies or pipeline barriers."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "To be consistent, I think it should actually just be a single `-`"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "this seems extraneous."
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "Ah, I see here that 'LongDomain' is defined as something that contains a subdomain segment that is `maxLengthOfDomainSegment` long (which I think is 63 characters) - I don't think any public ACME servers/Let's Encrypt's staging environment has a restriction on this?   if it does, and the 'pebble' based ACME server does not, then Pebble needs modifying to also fail in these cases as it aims to replicate the ACME RFC as closely as possible"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I think you need `-y` here to prevent a user confirmation prompt"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Repeating: I don't think this should be a core-wide global var. This should be isolated to arch/x86 or at least arch/, maybe inside getter/setters as mentioned above."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "right URL is like in cmdrunner, using search.maven .org"
    },
    {
      "prediction": "The valid syntax is described at https://github.com/grpc/grpc/blob/master/doc/naming.md.",
      "reference": "The link to valid syntax is not really applicable for NET2_1, right?"
    },
    {
      "prediction": "I don't think this is necessary.",
      "reference": "Shouldn't it be more specific, like \"gcppubsub supports all UTF-8 strings\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Everything in this class is SolrCloud-related, not legacy replication"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack.",
      "reference": "Could just assign directly and eliminate the `newval` var."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "... with the name of the affected package, or \"all\", followed by a colon,..."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We'll want to remove this one if we make the assembly version constant."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Can we have a single function here that uses the same subscribers and just changes meta based on context?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "where would ` static startup_kernel_loader skl;` be instantiated? if it's not instantiated anywhere should this be removed?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think we should move those util functions that work with drag-drop to @uppy/utils, so they can be shared (maybe later) with drag-drop plugin? Otherwise it will continue to depend on drag-drop module."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Migrate the spec.Labels to locator.Labels ?"
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "The test case already existed but it never tested properly because of the conditional in the test."
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "I'm okay with this, but I don't see a lot of benefit to removing unnecessary parens. If extra parens make something more readable (like this) or clarify order of operations even when matching the default, I would say we should keep them."
    },
    {
      "prediction": "This is a hack.",
      "reference": "@sarowe why was this volatile? It's fishy to see this as the only volatile field."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "template is not correct?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Rename the registies to `BBOX_ASSIGNERS` and `BBOX_SAMPLERS` to avoid ambiguity. There is also a registry for dataset sampler."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `--force` option.",
      "reference": "This is no longer stubbed on every test. Perhaps it should be, and should be unstubbed in the single case that it matters."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This seems much simpler! I'm not sure I follow what you mean by the threading part... Also tests are not liking this constant. Might need a require or to fully qualify this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Convention is \"FIXME: i#2144\" or \"XXX: i#2144\""
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This should probably be a property instead of a method."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "do we need to consider setting the `state` as well? If so, lot of changes might be required, like, setting to 'Reconciling' in upgrade code, setting to 'error' or 'reconciled' in volumeReconciler functions."
    },
    {
      "prediction": "I don't think this is the default processor chain.",
      "reference": "Line is too long. [82/80]"
    },
    {
      "prediction": "This file should not be used in the project root.",
      "reference": "Add blank line below license header."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not clear on whether this really should be the right behavior. Basically we're saying that a replace table will keep the existing location (as opposed to using defaults). I suspect we don't have create or replace with location semantics, but this is making some assumptions that a replacement is somehow the same as the old. If we were to go with id based pathing convention, this wouldn't work. I don't think this is an issue at this point, but it might make sense to push this down to the location provider."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `go.temporal.io/temporal-proto/execution`?",
      "reference": "Just run a global replacement for all `executionproto`."
    },
    {
      "prediction": "This is a hack.",
      "reference": "@AutomatedTester @davehunt thoughts on a new keyword argument?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Should line 47 be OPAE_ERR?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Not necessary, just write `time.Time{}`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "As these two strings simply get concatenated for the docs, there's a space missing after the dot here."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "What about integrations where we don't plug ourselved on OnMethodBegin?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "shouldn't **call** return a boolean?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "ViewModel classes should not expose any classes from framework.model."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "how would you feel about keeping these tests to be more explicit and having them `assert not _validate...`? or is your view that that is too duplicative of the tests in `test_evaluator.py`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why do we use the `winrm_nodes` variable here and not the string `\"winrm_nodes\"` as we were using before?"
    },
    {
      "prediction": "I think this code is a bug in vesoft inc. All rights reserved. I think this code is a bug in vesoft inc. All rights reserved. I think this code is a bug in vesoft inc. All rights reserved. I think this code is a bug in vesoft inc. All rights reserved.",
      "reference": "why update Copyright ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this mean we cannot update statistics with sampling on a table with LOB columns?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Look good, but I think a `[flags]` enum would be more future proof? Although i'm not sure if a flags-enum is working from the XML config. What do you think?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Since I believe state will never be anything other than 'expanded' or collapse, you can rewrite this as follows: `return row.treeNode.state === 'expanded' ? 'ui-grid-icon-minus-squared' : 'ui-grid-icon-plus-squared'; `"
    },
    {
      "prediction": "I don't think this is the case for the `id` field.",
      "reference": "the latter part can go but isn't the first part of this still sound -- that we assume \"id\"?"
    },
    {
      "prediction": "I'm not sure if this is a string, but it's not a string.",
      "reference": "Why is the escaping of @ and $ removed?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Nit: `Http` is redundant in this interface's name."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "what if I set SynchronizableEntitiesPrefix to \"a/b/c/d\" in config?"
    },
    {
      "prediction": "I think this is a bug in afero.",
      "reference": "nit: This error message doesn't mention that the path is a directory, maybe \"Dockerfile path is a directory:%s, please provide path to file.\""
    },
    {
      "prediction": "I think this is a bug in Garmin.",
      "reference": "This is done automatically, you can skip it next time ;)"
    },
    {
      "prediction": "I'm not sure if this is a tab, but it's not a vanished element.",
      "reference": "This is needed in `set_value` because of `:open-editor` (you could open an editor, close the tab, then close the editor). I don't think it makes any sense to have it here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Perhaps we can assume that profiling is enabled if ProfilingPort is set? And/or configure a default port and frequency, so we don't have to set three config vars every time?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "This nil check won't correctly handle the case where forward_ssh_agent is set to false - it won't be nil but it should still not be set."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We could avoid passing proto since threshold isn't needed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This route excluding needed for reconnect only when one connection is lost and we trying to establish another. I was thinking to make 2 separate flags for killswitch and reconnect enabling. This way we can keep killswitch working, but we don't need these routes excluded."
    },
    {
      "prediction": "I think this is a hack, but I think it's a bug in RocksEngine.",
      "reference": "why can this modification avoid crash?"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the account.access.disabled?",
      "reference": "This looks good -- signing out the user if the current user is disabled"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The line exceeds 120 characters."
    },
    {
      "prediction": "I think this is a bug in ddevapp.RenderAppRow.",
      "reference": "Let's go ahead and change \"Site\" to \"Project\", since that's the path we've chosen. One less thing to alter in the other issue."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I am for this change iff we are sure the information is no longer helpful. I think this could still be valuable for certain scenarios, wbu?"
    },
    {
      "prediction": "I don't think this is the case for the first imageRampup and maxImageRampup. This is the case for the first imageRampup and maxImageRampup. This is the case for the first imageRampup and maxImageRampup. This is the case for the first imageRampup and maxImageRampup. This is the case for the first imageRampup and maxImageRampup.",
      "reference": "I thought we decided on using the latest active version and not the one which is max ramped up."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "can we update this to a `log.Warningf`?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if it's connected to a network.",
      "reference": "can we get something emitted in the logs on non-zero exits to trace back to for problems like this failing on the first invocation?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need `schema manager` at here ?"
    },
    {
      "prediction": "I don't think this is a good idea to use `C.flux_parse_json(const char*)` instead of `C.flux_parse_json(const char*)` and `C.flux_parse_json(const char*)` instead of `C.flux_parse_json(const char*)` and `C.flux_parse_json(const char*)` instead of `C.flux_parse_json(const char*)`",
      "reference": "This won't work because of the permissions on the directory when this is included as a library. But, we may be able to do this. The key would be wrapping this command with either a script or a go binary that ensures the current directory is writable. If the current directory is not writable, it would attempt to make it writable so that we could write out the produced binary. But I'm not sure if that will influence the hash that gets produced for `go.sum` since I am not sure how that is calculated. Alternatively, we can choose a place in `/usr/local` or choose a location that is writable in the go cache and use that. I'll give that a try since it might be needed for the ARM builds if we choose to only include `x86_64` precompiled binaries in the module."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Correct me if I'm wrong, but is this necessary? Why not just use the value returned by `interpreter.Eval` and not mess with the scope? `interpreter.Eval` will return any produced side effects. This means TableObjects as well as any value resulting from any expression statements."
    },
    {
      "prediction": "I don't think this is the case for the `operated-alertmanager` field, but it's not the case for the `operated-alertmanager` field, so we need to add the `operated-alertmanager` to the `labels` field to the `labels` field.",
      "reference": "This service is global per namespace, not per Alertmanager/Prometheus/ThanosRuler instance. So this approach won't work. But maybe I missing out something, can you describe your use case here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need this default? Since we aren't using a sql.NullBool or *bool, an unset column will be interpreted as `false` already... We don't set a default on our other bool fields (e.g. entry admin and downstream columns)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "thanks for moving these over. makes more sense for them to be in the exports_helper"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the usertypes.enum('LastPress', ['none', 'filtertext', 'keystring'])",
      "reference": "That import now isn't needed anymore"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Can you update the `Usage` to be an absolute path as well? Something like `/path/to/firebug.xpi`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This class is missing the `MvxPlugin` attribute"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use wx.GetApp().SetTopWindow(mainFrame) instead of wx.GetApp().SetTopWindow(mainFrame) because we don't want to use wx.GetApp().SetTopWindow(mainFrame) instead of wx.GetApp().SetTopWindow(mainFrame) instead of wx.GetApp().SetTopWindow(mainFrame) instead of wx.GetApp().SetTopWindow(",
      "reference": "What if `wxLang` is returned `None` from `getWxLang`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please don't do changing like this unless it _**really**_ cares. BTW. Please look around to infer our naming conventions."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is in test code: understanding what we're doing is important in this context."
    },
    {
      "prediction": "I'm not sure if this is the case, but it is not the case. I'm not sure if this is the case.",
      "reference": "prob should still have an example that has multiple option names even if you have to make it up. Or maybe we don't need this method?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe respond_to whitelists the formats passed to the block so if we don't want to display html, we can just remove the line format.html..."
    },
    {
      "prediction": "I think this is a bug in `ddev list`?",
      "reference": "stylistic nitpick: I _feel_ like we've largely shown errors like this as \"error: \" vs. \"error=\". IMO colon/space reads better."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `history/BasicPayloadPool.hpp` and `history/CacheChangePool.hpp`?",
      "reference": "We could put this implementation in `RTPSWriter::create_change_pool` and avoid an extra function."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "should this file ends with _test.go?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It's because of this change. `ss` was unused and it made sense in the program. However I haven't read the IPv6 RFC so I'm unsure of what it does"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "\"Flatten\" is a verb, so I'd probably go with `flattenedIndex` as a variable name here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "If it can only be called once, perhaps a more appropriate name is something like `setMaskables`? `addX` sounds like you can add many `X`es by calling it many times"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Nodecfg should be downloading from a private bucket -- these shouldn't be for public consumption. In general these should be generic and expect environment to provide appropriate credentials and bucket."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Could you please end the file with an empty line?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is an incorrect change. The dialect spoken is an important part of the handshake and should be communicated to users."
    },
    {
      "prediction": "I think this should be a `struct{} `json:\"-\"` and `struct{} `json:\"-\"` and `struct{} `json:\"-\"` and `struct{} `json:\"-\"` and `struct{} `json:\"-\"` and `struct{} `json:\"-\"` and `struct{} `json:\"-\"` and `struct{} `json:\"-\"` `json:\"-\"` `json:\"-\"`",
      "reference": "Can this be non-exported to avoid direct use? It would be a breaking change but using previous package version would work."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Nit: this is just `return gcerrors.Code(err)`, isn't it?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't know where this came from, but it's not a good idea. This is actually timing out after 5 rounds, not 5 blocks. 5 consecutive null blocks won't be that uncommon. Also when testing with a short block time, this is a very short duration that can contribute to flaky tests."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "In Python 3 when pickling or unpickling objects, the file needs to be opened as binary so that no text encoding/decoding takes place. So for any open calls around pickle loads or dumps, the mode for reading must be rb and the mode for writing must be wb."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "did you remove **params.qstring.method** intentionally? if so why?"
    },
    {
      "prediction": "I think this is the default value for the default value, but it's not the default value for the default value, but it's the default value for the default value for the default value.",
      "reference": "What is the current default? Is that inconsistent across uses and that's why this is null?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why did we make this change? How come it wasn't an issue before"
    },
    {
      "prediction": "I think this is a bug in VkLayerTest, but I think it's a bug in VkLayerTest, but I think it's a bug in VkLayerTest.",
      "reference": "Can you tighten scope by moving to of these variables? i.e. Move to ~4372?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is the right thing to do.",
      "reference": "Nice to see this `dataverse.rserve.password` fix rolled in."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How about the following faster alternative that doesn't need `strlen()` at all: if (*tmp_optarg == '\\0' || *endptr != '\\0') { fprintf(...) ... This would treat the bus argument as invalid if it's either empty (`tmp_optarg` points to '\\0') or invalid (`endptr` points to something other that a '\\0'). Actually, the existing code would accept an empty argument and set the bus to `0`, so if (*endptr != '\\0') { fprintf(...) ... would be enough. The check for an empty argument doesn't hurt, though."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I could be missing something here, but the `from` and `cc` are the same. On the test email sent to gatewaycommunicator, these values are different."
    },
    {
      "prediction": "I don't think this should be called twice.",
      "reference": "I'm honestly scared because act is now a hard requirement for useEffect which it wasn't before... This could break some tests :("
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could use election from `info_a.election`, or is this deliberate?"
    },
    {
      "prediction": "I think this is a bug in Symfony 4.2.",
      "reference": "looks like this should be `return array(LegacyFormHelper::getType('form'));`"
    },
    {
      "prediction": "I'm not sure if this is a mocha callback?",
      "reference": "Maybe it would simpler to ignore opt_port if type !== 'number'?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Where was `name` being declared before?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "nit: use `corev1.ConditionUnknown`"
    },
    {
      "prediction": "I'm not sure if this is a valid object id?",
      "reference": "You also need to add a similar check on line 992, there's another place where we check `length === 24`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: can extract the voteProvider as a local variable"
    },
    {
      "prediction": "I think this should be a test, but it's not a test, but it's not a test, but it's not a test, but it's not a test.",
      "reference": "[0] Not suggesting you change it here, but....kindof weird that there's just not an `assertFuncNotEquals`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why are we passing 'registryAddress' here? We probably should construct it together with bc. Registry is not something that change?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`.` at the end of the sentence"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "wouldn't it be useful to split this into an error metric for the timing?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure if this is good enough. Each generator will have it's own unit test anyway. Ideally, I think I'd want to test that each generator in the yml is actually a valid generator..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "line is 138 characters"
    },
    {
      "prediction": "I think this should be a function that calls Close on the returned database.",
      "reference": "Nit: I would leave `Wire` out of the description; if you use this without wire you can still use it."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Nit: each field can be on a separate line to make it visually easier to read."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Do we still have these files? Shouldn't we remove these?"
    },
    {
      "prediction": "I don't think this is a bug in this package.",
      "reference": "A lot of things to do with constants seemed to move since the original commit, so I stuck this here, Is there a better place for it?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "is 10 too small compared to 1000? consider sync chan is unicast only (vs block chan is broadcast + unicast), i would say use 200~400 for BlockSyncChanSize my concern is that this would potentially slowdown sync speed of full-node"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure if this is the case.",
      "reference": "A full parse of the plan here on listing the plans will be expensive from both a computation and IO perspective."
    },
    {
      "prediction": "I don't think this is a bug in NRF52840-DK.",
      "reference": "These constants use the `_PIN` suffix, while the other constants don't use it. I'm not sure what is best, but I would prefer to keep this consistent. Do you have an opinion on which it should be (with or without suffix)?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Hmm... this feels like discovery should come first. perhaps `--discovery-dns-url`? @NicolasMassart any opinions on this or ideas on who it should be run by?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "why is this needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I wonder if it'd be possible to autogenerate a key from the name within this function if one is not provided explicitly, rather than having all the callsites pass both the name and key (and usually as the same value)? Might give us a good place to implement a `name->key` function that isn't 1:1."
    },
    {
      "prediction": "I think this is a hack, but I think it's a bug in the code.",
      "reference": "@adriancole I do not see a change in the thrift file. Are there unit tests verifying that this manual serialization is compatible with the native Thrift serialization done by classes generated from `.thrift` IDL file?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "spelling (variable name, all three changes)"
    },
    {
      "prediction": "I don't think that `desiredKeyGen` is set to `UnspecifiedKeyGen` and `desiredUID` is set to `UnspecifiedKeyGen` if the server check is required.",
      "reference": "I believe you meant \"specify `desiredUID` and `desiredRole`\"?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Please follow the import style, move it to its similar group"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Do we really need these? This is expanding on an API that we're about to do work on with the error stuff @kriskowal"
    },
    {
      "prediction": "This is a hack.",
      "reference": "passwordModificationTime is no longer used - did the change drop a time check that should be restored? Or should the param get dropped from the methods?"
    },
    {
      "prediction": "Should we remove this?",
      "reference": "Would it break here without trim? If so, can we do trim in Startup.cs so we don't need to add this code to every parser?"
    },
    {
      "prediction": "I think this should not happen.",
      "reference": "Since we're using Logrus, probably best to use `Infof` to avoid confusion (Logrus' Printf behaves differently to the built in one)"
    },
    {
      "prediction": "I'm not sure if this is a label?",
      "reference": "Hm, this looks like a change that should go upstream as well."
    },
    {
      "prediction": "I don't think this is the case where we don't have an action index.",
      "reference": "let's keep ActionByActionHash and delete getActionByActionHash"
    },
    {
      "prediction": "I'm not sure if this is a PricingGroup, but I'm not sure if this is a PricingGroup.",
      "reference": "please use return type"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is deliberately at this level."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "I'm going to go ahead and undo this change, I don't think it was intentional."
    },
    {
      "prediction": "The following logic is further specialized, depending on the kind of the current AppDomain and where the app is hosted:",
      "reference": "> specialised This isn't a typo in my neck of the woods  "
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "will change to `storage_target`"
    },
    {
      "prediction": "This is a hack.",
      "reference": "This would be better as `cls.securitycenter_client`, to match what is being instantiated."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we have this initialization as part of the initialize method?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This line should be removed as editController is not used from this context anymore."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is correct in concept but the method signature doesn't really communicate the same thing. In other words, if the function produces an output table where is it? Its not on the function signature. Can you explain where the output table is created?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For insurance, it's best not to take it directly"
    },
    {
      "prediction": "I'm not sure why this should be done in the future.",
      "reference": "change 'value' to keysToSend, here and in other references in this commit. 'value' implies the user is getting the value of the element, rather than just the keys we're sending to it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "is the plan to fully migrate to boltdb and then remove the state save here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This should be `output.colorBright`. Unless I'm missing some reason for adding a new theme variable."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: I wonder if these should be moved down to where version is defined, just to keep them all in the same place."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this supported by every implementation of Java (and Android)? Should it be conditional upon `gen_nullable`?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `sections.number` and `sections.phase_id` where `sections.number` > 0, and `sections.phase_id` where `sections.number` > 0, and `sections.phase_id` where `sections.phase_id` where `sections.phase_id` where `sections.phase_id` is not `sections.number` where `sections.number` is `sections.",
      "reference": "@briri Thanks! I just caught this too updating my feature branch"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think you should move this block (and the `envpw := os.Getenv(\"RCLONE_CONFIG_PASS\")`) right to the start of the function, then we can remove the duplicate code below"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Is this only to set the node to draining?   I think we can do that inside `Before` or something?"
    },
    {
      "prediction": "I don't think this is the best thing to do with the `AzureAppServices.Metadata.IsRelevant` flag.",
      "reference": "This should have been moved up above this inner `try` because the log message in the `catch` block does not apply to this."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Do we expect people to use PlanResult directly?"
    },
    {
      "prediction": "I think this is not a good idea.",
      "reference": "Maybe we should call this something like `errToReturn`?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "should calculate numEpochIn1Year = xxx and <= fairBankEpochNum+numEpochIn1Year a.foundationBonusLastEpoch just happens to be equal to 1 year now, but should not count on that"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I wasn't sure if the content type needed to be removed from both the `default` and `usemap` objects - I'm not sure how usemap is used."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Duplication of line 28 Please refer your tox -e flake8 It seems that XStrField, XShortField, FieldLenField are not used"
    },
    {
      "prediction": "I don't think this is the case for the `_to_complete` field.",
      "reference": "I don't really understand the `self._file_model.index(path)` as parent here - you use `self._root_index` for `rowCount` above, so wouldn't the parent here need to be `self._root_index` as well?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Do we want validation somewhere that max >= min? Or simply treat the max < min case as ignoring max?"
    },
    {
      "prediction": "This is a hack.",
      "reference": ":+1: that's a easier example :)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "If an external module decorates this interface, such a change will cause it to generate an error"
    },
    {
      "prediction": "Should we remove this?",
      "reference": "Oh ha hah, FNM_PERIOD worked out nicely there. Points for co-opting a file system convention."
    },
    {
      "prediction": "I don't think this is the right thing to do with this, but I'm not sure why this is the right thing to do.",
      "reference": "wrong grouping. As you can tell from the other files, we put system packages in the first group, the 3rd party packages in the second group, and our own packages in the third group."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is `o.name` always set here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can this line be removed, as `SteadyStateDependencies` isn't updated anywhere? Also do we need to check the `TransitionDependencySet` here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`plan.present?` and `has_active_subscription?` are equivalent. We can drop this change, while leaving the one on `app/controllers/application_controller.rb`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "No need for this, as pylint already only turns things off for this function and it's needed for the entire function."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "L171 needs to be modified too?"
    },
    {
      "prediction": "I don't think it's a bug in this file.",
      "reference": "Why do you compare by nodeid? Simply saying d == e should be enough. Unless we have to objects in memory with the same nodeid. If that is so, something went really wrong."
    },
    {
      "prediction": "I don't think this is a problem with the `pyramid_vision_transformer`",
      "reference": "configs/pvt/retinanet_pvt_t_fpn_1x_coco.py --> configs/pvt/retinanet_pvt-t_fpn_1x_coco.py"
    },
    {
      "prediction": "I think this should be a string, not a string, but it's a string, but it's not a string, but it's a string, but it's a string.",
      "reference": "Nit, this could be json:\",omitempty\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It's kinda funny to read `s.Image.Image` I wonder why it resulted to this way. What would it take to refactor to just `s.Image`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: I like the idea! can we instead change the tag to `integration-remote` to be more specific? I feel like it's possible for us to use the `deploy` build tag for possibly another scenario"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Copy and paste error here. Edit: Also missing commas here and in other Perl croaks between some parameters and not others."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "stateRoot or maybe ParentHeader would make more sense from API point of view?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Are you sure that this is no longer needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would it help to use SCAN_COLUMNS as base to build SCAN_WITH_STATS_COLUMNS e.g like so `SCAN_WITHSTATS_COLUMNS = ImmutableList.<String>builder().addAll(SCAN_COLUMNS).add(\"value_counts\",....).build()` ?"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea to use the `ReportStat` service.",
      "reference": "`ctx` is unused in ReportStat"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We don't want to add boost as a dependency when building the Thrift compiler. Sorry."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "It's not printing the range. Also I think it's useful to print a warning above stating that the minimum change is -1000."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "if name is empty will this become enumerate ? (and cause the unmarshal to fail ?)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with a link to edit_subscription_path?",
      "reference": "How about including a flash message that explains the exercises are only available to subscribers of X plan?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "You should also call `e.accept()` and `return` so the key press isn't processed further (as we're leaving insert mode anyways)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Freeze mutable objects assigned to constants."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `waitForResponse` method.",
      "reference": "Hmm, this feels hacky. Maybe good enough if it makes the test more stable, but why is timing even an aspect here, since below it should wait for these two things anyway?"
    },
    {
      "prediction": "I don't think this is a bug in OpenTelemetry, but I don't think it's a bug in OpenTelemetry.",
      "reference": "Do we want this on by default, or an opt-in (e.g. via some config while add the instrumentation)? I guess a more general question is - what's the bar for the default vs opt-in tags."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`status` is just one of the features, named as status is not suitable."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "There is an option to hide the subscriptions list from the sidebar. If it is hidden, the filter text should not be displayed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd like for all of this to be dynamically configurable at some point, but it doesn't have to be in this PR. Can add it to the future SIP or create a separate JIRA for it, as you think would be appropriate."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "move the constructor to down the `namespace`"
    },
    {
      "prediction": "I think this should be a string, not a string.",
      "reference": "Nit: ending with a '.' looks consistent with the fields around it."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Audit log will not have a warning about they are using a deprecated path, is it something we must care about?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think you also want to update the condition to add ` || impl.Visibility == TypeMemberVisibility.FamilyOrAssembly`."
    },
    {
      "prediction": "I don't think this is the correct value for `depositToRewardingFundGasPerByte`?",
      "reference": "`DepositToRewardingFundBaseGas` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "What do you think of \"operations\"?? Also what do these emojis look like on Linux??"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "I like the word \"give\" here. Feels like I'm giving a gift to my team."
    },
    {
      "prediction": "I don't know how to do this, but I don't know how to do it with the `make_multilabel_classification` function?",
      "reference": "Is it possible to use `np.random` module instead?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "``default=None`` implies ``allow_None`` so ``allow_None`` is superfluous here. As a special case, if allow_None=True (which is true by default if the parameter has a default of None when declared) then a value of None is also allowed."
    },
    {
      "prediction": "I don't think it's hardcoded to k3s-controller in the rolebindings.yaml",
      "reference": "Is there anything in particular that makes setting up the downstream rolebinding(s) to `system:k3s-controller` burdensome or confusing? This changes looks fine to me but it seems a shame to alias an embedded k3s controller. If we are doing this in other places that I am not aware of then we can dismiss this concern out of hand."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "This file should be included in the project root directory.",
      "reference": "nit: all other types in this project have full names, so maybe a better name would be `OperatingSystem`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the namespace MolTransforms.h?",
      "reference": "Why is this needed here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "mmm, why a method declaration should not have the TypeVariableResolutionCapability? Is this ok?"
    },
    {
      "prediction": "I think this should be a privateTransactionHandler, not a privateTransactionHandler.",
      "reference": "nit: any reason you swapped the ordering?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `data-codec` attribute.",
      "reference": "can you de-uglify at least this line?.. hard to tell what changed..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please can you merge master in before making these changes. I just reinstated a bunch of BPF UTs. Possible that the UTs use this code."
    },
    {
      "prediction": "I'm not sure if this is a class method, but I'm not sure if this is a class method.",
      "reference": "Do you want to add additional cases for `Bla.__b()` and `self.__c()`? (Just add additional classmethods `__b` and `__c` and the calls to `__init__`)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "the recids is never changed after. So, it should contains the exact shown results, whatever are the rights for the user (admin or simple user, restricted collections...)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't the docstring mention that the MD5 checksum of `p` is computed each time and verified? Also, could there be use cases where a caller might not want such a check to happen because, eg, a blob storage solution doesn't provide MD5 verification or uses another hash algorithm such as SHA256?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "focusRedirect is used in the powerpnt appModule. We might have to make sure that this does not break. Having said that, I really like this being handled on the events level!"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "You imports are out of order"
    },
    {
      "prediction": "I think this is the default job name.",
      "reference": "This should not be called Flow Trigger. FlowTrigger should has its own flowTrigger job name, for instance, \"flowtrigger\""
    },
    {
      "prediction": "I'm not sure if this is the right thing to use.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Why do we need `\\n` if we already use `WriteLine`? (and `\\n` is not cross platform)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is instrumentation name used for? I'm not seeing other classes use it, only a getter, constructor, and builder."
    },
    {
      "prediction": "I think this is a bug in Nethermind.TxPool.",
      "reference": "@kristofgazso could you review these warnings?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "will delete this."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `new_individual_plan_purchase_path` method.",
      "reference": "~~Indent 2 lines above~~ Disregard. My fault"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "What was the bug that this is fixing?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This will always add the authorization header to the request object. Is this the right scope for these two lines? If username/password are not defined, it will encode 'Basic :'"
    },
    {
      "prediction": "I don't think this is a bug in the flatbuffers package.",
      "reference": "Is this always how Bazel does paths? Would it be nicer to do `-DBAZEL_TEST_DATA_PATH=../com_github_google_flatbuffers/tests/` so this string is not hardcoded in the the source?"
    },
    {
      "prediction": "The `date_utc` parameter is not used in the `update_id` and `target_doc_type` parameter.",
      "reference": "Not an expert of ES, so not sure of the impact here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Who deletes the memory for the granteeList? (or the roleList for that matter)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This loop is missing a lock on subscriptions_mutex."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "shouldn't clearance be setting these up for us?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Need to update the doc for `TelemetrySDK` and `Host` structs deleting references from removed functions."
    },
    {
      "prediction": "I'm not sure if this is a final record.",
      "reference": "I think we should keep that here and add a new method `isSyntacticallyFinal` that returns `super.isFinal()` (and can be used in UnnecessaryModifier). Otherwise the contract of `isFinal` is not respected"
    },
    {
      "prediction": "I don't think this is the right place to see the row.",
      "reference": "Is there a reason why we wouldn't want to check this every time? Why are we only checking for the footer and scroll bar when enableCellEditOnFocus is true?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "You need to create an API for this class. This class should follow roughly the same dependency structure than RemoteAvailableInstallersPlayOnLinuxImplementation / RemoteAvailableInstallers. Maybe we could use a inner class here?"
    },
    {
      "prediction": "I don't know why this is the right thing to do with `workflow_type_name` and `close_time` in `workflow_type_name`, `status`, `history_length`, `memo`, `encoding`, `status`, `status`, `history_length`, `memo`, `encoding`, `status`, `status`, `status`, `status`, `history_length`, `encoding`, `memo`, `encoding`, `status`, `status`, `history_",
      "reference": "This should not be a case, right? If `run_id` is the same `workflow_id` can't be changed. Actually surprised that it is not part of a key."
    },
    {
      "prediction": "I think this should be removed.",
      "reference": "How would AQR work for an INSERT/SELECT of one table into another where a LOB column is being copied?"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Since these are ultimately different endpoints, it would be nice if we could move them up one level and nuke the common `sds` directory in order to reduce path stutter"
    },
    {
      "prediction": "I don't think this is a good idea to use `beforeChangeResult[0]` instead of `beforeChangeResult[0]`.",
      "reference": "Please check also whether `null` occurs in the rest of `beforeChangeResult` array."
    },
    {
      "prediction": "I'm not sure if this is a client side filter.",
      "reference": "Outdated docs. There is no response, there's an ack."
    },
    {
      "prediction": "I'm not sure how to do this with `libcontainer.InitContinueSignal(libcontainer.InitContinueSignal)`?",
      "reference": "I'd rather have the container process remove the FIFO after it unblocks. Then `start` can always `Exec()`, and you can catch the \"FIFO does not exist\" error and translate it to a prettier \"someone must have already started the container\"."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "can you check if there's other similar cases to add nil-check like this?"
    },
    {
      "prediction": "I don't think it's a valid commonname, but it's not a valid commonname.",
      "reference": "`<= 64`? I just picked up what you said in #3981 (\"the CN field is limited to 64 characters\") but maybe there's something I don't know where the 64th character is needed (trailing dot or whatever?) Also this sounds like something that could be beautifully unit tested. Sorry for bugging you :grin:"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I understand that this grabs a Licenses objects but what is the autocomplete method used for? What does this do in context of the auto_completes controller?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't really like that way of naming methods based on their arguments. But I can see that the other method names are the same ..."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@sekmiller This method correctly strips the leading and trailing slashes (and also \".\" and \"-\"); But I thought the plan was also to replace any multiple slashes between nested folders with a single slash. For example, as implemented now, I can enter \"folder1///folder2\", and it gets saved and displayed like this, with the 3 slashes. I thought we wanted to sanitize it as \"folder1/folder2\"."
    },
    {
      "prediction": "I'm not sure why this is a bit of a hack, but I'm not sure why this is a bit of a hack.",
      "reference": "Looks like the X86 inline assembly is not happy with this type. I will update that"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Tabs and a space, again."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Please just enclose if blocks with brackets; this has created issues in the past so I'd prefer we don't use them"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `approve_response_path(approver_action: 'approve', cart_id: @proposal.cart.id, version: @proposal.version)`?",
      "reference": "`version` isn't need anymore because it's built into `approve_proposal_url`, yes?"
    },
    {
      "prediction": "I don't think this is a bug in scapy.layers.dot11.",
      "reference": "Moved to the bottom of the file. `CtrlPDU` sits on `BTLE_DATA` so let's put it after"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This ends up requiring the `json` gem, right? Is there any way we can do this to be implementation agnostic (e.g. to let me use `yajl-ruby` for performance reasons (or because my app already brings in a JSON library)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This seems dangerous. What circumstances lead to the need for a retry? Can that happen more than once? I'm concerned that if we hit the pathological state, this could turn into a CPU spinner. I wonder if we could get the same benefit from just \"trying again\" and failing if it fails the second time."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "If there is a reference to other fields or methods, please do the initialization in the constructor."
    },
    {
      "prediction": "I think this is a hack, but it seems that the `__examples__/base.jsx` file is not in the `__examples__/icons.jsx` file, but it seems that `raw-loader!@salesforce/design-system-react/components/pill/__examples__/avatars.jsx` file is not in the `__examples__/bare.jsx` file.",
      "reference": "These should be importing from `pill-container`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Why this change? It will now only show on the bottom of the screen as white text, is it correct behaviour?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Does this need to allocate a string or would a nil value (indicating no header) be a better?"
    },
    {
      "prediction": "I think this is a function, but it's not a function.",
      "reference": "Nit: Past tense of `reset` is also `reset`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't this use `'n'` instead?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "revert back to 'TASK_TYPE_ACTIVITY_TIMEOUT'"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Shouldn't we prefer passing a pointer by reference T*&, since these are C++ bindings?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: Personally I feel that it's cleaner to let `toAntreaPeerForCRD` to take `ingressRule` as a param instead of `ingressRule.From`. It can call `processRefCGs` inside the function and do the ipBlock/AG union within the function itself. It might not be worth the refactor though."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Pending has been set only for SPC.. why? for other CRs as well, this need to be done.. right?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `src` parameter.",
      "reference": "would use an empty string here as default and then check for emptiness in the twig template. I dont like mixing types @core23 what do you think?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "How come we need case manipulation for the nextPageToken and not for pageToken?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "why use these rather than regular named paths?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Hm, I don't think the extra flags are doing any harm here, but it does seem like `--help` is the only flag you could *actually* use with this command. We might eventually want to separate those out."
    },
    {
      "prediction": "I'm not sure if this is the case where the user is listened to in the last 7 days listens.",
      "reference": "We should make this a docstring, so that editors are able to pick it up."
    },
    {
      "prediction": "I don't think this is a problem with the `.locked-message` attribute.",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "App cache size is now managed dynamically by the `WebView`. This statement has no effect in the new framework."
    },
    {
      "prediction": "I don't think this is the case for `img` or `input` or `area`?",
      "reference": "VirtualNode has a `hasAttr` function, any reason why you're not using it?"
    },
    {
      "prediction": "I think this should be called once per process, but it should be called once per process.",
      "reference": "This now throws when running tests (maybe the move to java 11??). Do we want to keep it?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "We can allow 7-char SHA, does not mean we want to show with 7-char in default, please change to `if len() > 10`, then cut."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "this one should also have quotes i guess :)"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "Using the variable on range scope `mock` in function literal (from `scopelint`)"
    },
    {
      "prediction": "I don't think this should be a good idea.",
      "reference": "does this result in a 200 when the dataset is still inprogress/publishing not yet finalized? Seems like 202 is the right code for that (as it was) and the test should be watching for a 202?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Previously you could only order by the field you were searching by. But for full-text search, you can search across all indexed fields, and it didn't make sense not to have a sorting. For backward compatibility, the javascript code uses indexPath as the orderPath when no orderPath is provided."
    },
    {
      "prediction": "I don't think it's a `VNode`?",
      "reference": "VIM didn't like your whitespace."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Are you sure the namespace should change?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "@martijn00 I'm not sure why we're keeping the object parameter and return type since this can be done by using MvxApplication<THint> with THint set to object"
    },
    {
      "prediction": "I think this is a bug in MySQL.",
      "reference": "why do we create a time type here?"
    },
    {
      "prediction": "I think this is a hack, but it's a hack.",
      "reference": "Does this style actually need to get loaded in all of these components?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "import but not used so you did not resolve compile warnings?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is so much more concise and beautiful than the previous formula  "
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is there any reason not to have the `static` modifier for the logger? _(that would be in keeping with the reference being uppercase)_"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "It's not about session creation config. It's about passing consumer config parameters to underlying transport - nothing to do with session itself"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is there an \"enable\" in the param name? Couldn't it just be `overrideDebug`? Here are everywhere else."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`published.recently_published_first` reads a little oddly to me. Is this the same thing as `Video.published.ordered`?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Encountered this because I had a stray comma. Figured I'd tweak it a bit."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "qq: Should this include the iptables6-save sim. to the inverse checks above?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "im open to explicitly checking NotSet value here but json logic already handles it so kept it this way."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The naming of the include file appears to be unlucky."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Bit worried about this. At minimum you should make a copy of the dict here to avoid modifying a user supplied variable."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is it better to create one before pruning? In case creation fails we don't want to delete the previous one. We create a new one, it is tagged as latest, so the previous can be deleted. `CreateLaunchTemplateVersion` returns the version created, how about directly trying to delete the previous version? Assuming the numbering is strictly increasing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we require the specific implementation information here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `email_banned?(email_address)` and `email_banned?(email_address)` and `email_banned?(email_address)` and `email_banned?(email_address)` and `email_banned?(email_address)` and `email_banned?(email_address)` and `email_banned?(email_address)` are the same as `email_b",
      "reference": "How about `exists?(['domain ~* ?', domain.downcase])` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this getting used in other places? Can we switch all the places to use the new API you added?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `curl_easy_setopt(curlEasy, CURLOPT_CAINFO, CA_BUNDLE_FILENAME);`",
      "reference": "This need to be checked with linux. AFAIK, we have this file in our bin directory that is a link to the system file."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `options.controllerFactory` and `options.controllerFactory` are the same as `options.controllerFactory` and `options.controllerFactory` and `options.controllerFactory` are the same as `options.controllerFactory` and `options.controllerFactory` but `options.controllerFactory` are the same as `options.controllerFactory` but `options.controllerFactory` are the same as `options.controllerFactory`.",
      "reference": "Shouldn't we import `default`? I can't get here to test."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `run_server` method.",
      "reference": "!!!!!!!!!!!!! @graingert, does this mean that tests haven't been running???"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I've already tried the null-coalescing operator here and got a strange error, so did this the old-fashioned way."
    },
    {
      "prediction": "I'm not sure if this is a list role, but I'm not sure if this is a list role. I'm not sure if this is a list role.",
      "reference": "This doesn't follow our spacing convention. It's also a little hard to read. Can you reformat?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "The deploy should come before template? EDIT: I see that in other files, we put a separate line and put deploy at the end. What is the reason for this?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Consider making a constant (e.g. `MetricStreamConfiguration.Drop`)."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "same question: why not just switch this to range too?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "@chuckatkins most places used an empty string for \"no type\", but a few used `\"unknown\"`. I've converted both cases to `Type::None`. Do you know why there was a distinction before?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we assert for the type for `FeatureGroupData` ? I think it should be 1-Byte type."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "As long as you are sure this is definitely correct now... :-)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "... so that all action buttons have the same height :-)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Use correct, alpha sorted, include order. Correct order means: 1. Header corresponding to this source (i.e. `\"LatencyTestPublisher.hpp\"`) 2. C system headers 3. C++ system headers 4. Alpha-sorted external libraries headers 5. Alpha-sorted public headers from this project 6. Alpha-sorted private headers"
    },
    {
      "prediction": "I don't think this is the default implementation.",
      "reference": "I hate this name, open to suggestions."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this log line work? We need Warningf or just warning without the format string."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The pull controller would need similar updates."
    },
    {
      "prediction": "I don't know if you can use this file except\n.",
      "reference": "ignore this.. just didn't want to litter with a commit update to satisfy license plugin"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the msi installer.",
      "reference": "Is this definition needed since it doesn't look like it's being used anywhere?"
    },
    {
      "prediction": "I don't think this is the default, but it's the default, but it's the default.",
      "reference": "Can this condition be reworded using `if` please?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "after ||, no need inputs != nullptr"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Is it just preference or on purpose that using slice of structs instead of slice of pointers?"
    },
    {
      "prediction": "I don't think this is the same as `oldVNode._dom` but it's not the same as `oldVNode._dom` but it's not the same as `oldVNode._dom`.",
      "reference": "This line always confused me   anyway. Good catch!"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Should we add `ctx` to `BlockServer.Shutdown()` for this purpose? Would be nice, but I don't care too much."
    },
    {
      "prediction": "I think this is a bit of a hack, but I think it's a bit of a hack, but I think it's a bit of a hack.",
      "reference": "Duration_t at RTPS level must be serialized using fractions."
    },
    {
      "prediction": "I don't think this is a bug in YARPC.",
      "reference": "\"peer\" has its own meaning within YARPC with its own class of objects. This should probably be \"dispatcher\" too?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `-Xclang` command, but it seems that the `-Xclang` command does not have the `-Xclang` command.",
      "reference": "I do not like this line break before `=true`. Maybe starting the list in the next line would help to reduce the indent? This way we could keep this string together."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "_plugins should be removed too"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "The rule selector will not include `<input>` and `<area>` elements. Why not make this a new, separate rule altogether?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "@The-Compiler Is this style okay or would you prefer a common userscript exception base?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "we'd need to return a MongooseBuffer here instead of the Binary. lets add the subtype option to the buffer schema type as referenced in #1000 instead."
    },
    {
      "prediction": "I don't think this is a good idea to use `options` instead of `callback`?",
      "reference": "Let's remove this change."
    },
    {
      "prediction": "I don't think this is a change event.",
      "reference": "Could you split this into multiple lines?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the current entity URL?",
      "reference": "This technically works, however it may be safer to use both `getCurrentReferenceURL` and `getCurrentEntityURL` and then make this condition `currentReferenceURL === currentEntityURL`. Currently, this code only works based on the internals of `getCurrentReferenceURL`, so by checking both we would decouple that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It does not recommend capitalization"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to do it with the `submit_declining_credit_card_info` method.",
      "reference": "Minor thing, but can you use 1.9 hash syntax for this?"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I tried to follow the code structure already present."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "seems reasonable to also want to include the 'to' location?"
    },
    {
      "prediction": "I don't think this should be needed.",
      "reference": "Please leave 1 space char between commas here and other places in this PR."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "hm is this really &&? Not ||? Was it initially correct if any of these things are not set that it needs to recreated?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Please don't use C-style array declarations. IMO our pre-commit ought to be enhanced to not allow this"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "@rhc54 This doesn't look like a comprehensive comparison. For `PMIX_STRING` we seem to actually compare the content of the data while here we only compare meta-information which doesn't ensure that values are the same."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think `bypass_frontier_confirmation` conveys the intention better (default false as well)"
    },
    {
      "prediction": "I don't think this is a bug in the filecoin-project.",
      "reference": "This looks like it goes beyond the scope of removing `BlockHeight()`, in the future please do this in a separate commit at a minimum -- separate PR is fine too."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `parent` argument.",
      "reference": "You'll also need to adjust `FakeWebTabAudio` in `tests/helpers/stubs.py`."
    },
    {
      "prediction": "The \"License\" is not included in this file.",
      "reference": "@csrwng what should we do here? This one is from origin."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Follow alphabetical order."
    },
    {
      "prediction": "I don't know why this is the case for the `IAutomaticTracer` interface.",
      "reference": "As far as I can tell, these always get and set the context as an `IReadOnlyDictionary<string, string>`. Can we use that here instead of `object` and get rid of the `as IReadOnlyDictionary<string, string>`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "As you only have `{}` as the format string (without anything else in it), this is the same as doing `self._doc.setHtml(html.escape(self._opt.text))`"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Where would this be configured? In azkaban.properties?"
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "1. Use `const` instead of `var` here. 2. Move the check to after the `if (update == null || typeof update !== 'object')`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Let's assume that on Linux `eventfd` is always available as a wrapper of the eventfd2 system call. It is supported since linux 2.6.27 + glibc 2.9, as well as from the ancient versions of bionic. In other words, it would be fair to argue that the pair would be available on practically all platforms that provide `pipe2`. Therefore switching from using `pipe2` to `eventfd` on linux unconditionally would not cause issues on our users."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This field could be `final`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "would be good to have a test for the case when `shutdown!` raises"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Does upsert pass this check also?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Apologies reviewers, I did end up pushing another change. I was starting to request SRE-P help to get the apiserver configs from some clusters before and after when I realized I can just log the stdout from the patch command to see if anything was changed or not. Much simpler to verify if my work did or did not make changes to the config during the transition. Also got the spacing issue you mentioned @abhinavdahiya Thanks all."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `_kbfs_config` variable.",
      "reference": "I'm not sure this naming is a good idea; that's the format for macOS xattr metadata files on unsupported filesystems."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Metrics/LineLength: Line is too long. [85/80]"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please remove these imports. The project's style is to use `Assert.assertEquals` and not import static methods in general. This also caused a lot of unnecessary changes."
    },
    {
      "prediction": "This is a hack.",
      "reference": "thanks. Note that returning at this point might leak memory from the allocations above, so the PR will need to take care of that too."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If you really want to rename this, you'll also need to adjust the name in `__init__` and in other places it's used (`browser/commands.py`)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "As discussed at standup, I gave up on this. Calling `DeleteMapLayerMetadataCommand` felt cleaner anyway because there might be other cleanup that needs to happen. @scolapasta and @matthew-a-dunlap plan to discuss this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need these changes? If so, can you tidy up the messages? Looks like it might have been your testing/debugging changes  "
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "where is the default being set?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "these changes should likely be in the next commit instead"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since you have defined this struct, I would suggest to replace all exist literal structs by this."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The field name doesn't really capture what this option does. I think `mConfirmDiscardMessage` would be a better choice."
    },
    {
      "prediction": "I'm not sure if this is a string",
      "reference": "what if `$media->getBinaryContent() == Symfony\\Component\\HttpFoundation\\File\\File` does `is_string()` return `true`? ping @greg0ire"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "maybe rather than `bool` make this field a `StructDef *` ?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Shall we maybe put this in a `const` like `backgroundTaskTimeout`?"
    },
    {
      "prediction": "I think this is a bug in Datadog.Trace.TestHelpers.",
      "reference": "CI is complaining about this."
    },
    {
      "prediction": "I'm not sure why this is a good idea, but I'm not sure why this is a good idea.",
      "reference": "Let's only change a file if it is really necessary. Such a change does not bring much value and makes it harder to find the original commit in which the method was introduced."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I would prefer to set up space between classes in format pattern, `%s %s` and then use `trim()` to remove unnecessary whitespaces. This will also solve stripping whitespaces from the beginning and end of a string `$attributes['class']`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "when Op is illegal should return here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "don't we need to remove the project version from installedVersions?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `page_ranges` option.",
      "reference": "the bridge here isn't defined as an accessor / reader to try mask it better. So you need to directly call the iVar `@bridge` here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is intended. Pls revert this."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Something wrong with cast to `(Comparator<> & Serializable)`, need to be investigated"
    },
    {
      "prediction": "I think this should be a `filter` method.",
      "reference": "I think we need this. Not sure, I'll test."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I'm going to need to check if google compute requires these steps in this order, or if you can disable iptables after the fact."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `build/static/charts/traefik-crd-10.3.001.tgz` or `build/static/charts/traefik-crd-10.3.001.tgz`?",
      "reference": "Did go change their tags with the new version?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I don't recall what we decided here in terms of which source would get priority. As written, the static configuration will overwrite datastore results."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "I think it should still panic for when there are no outputs; might be nice to special-case that though so the message is more explicit."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "*NULL_DEREFERENCE:* object `null` is dereferenced by call to `meterSupplier(...)` at line 122."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "switch over to .mode"
    },
    {
      "prediction": "I'm not sure why this should be done here.",
      "reference": "I guess your IDE did some auto-fixing here  "
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I",
      "reference": "This is an unused import failing recommit still."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm concerned that we're conflating multiple things here. There are 2 things that Beaker should really care about: - Network transport - i.e. `ssh` vs `winrm` - Interpreter - i.e. `bash`, `cmd`, `powershell`, etc The problem is that @cowofevil is running Bitvise SSH, and he assumed we should be setting `is_cygwin: false` in node definitions. But that doesn't really accurately convey what we care about, and since Beaker doesn't appear to track network transport apart from interpreter, we end up in a strange state. `is_cygwin: false` appears to end up setting `is_powershell?` to `true`, which IMHO is not accurate or appropriate. Bitvise templates use `ssh` (like Cygwin), but the interpreter used is `cmd`, not `powershell`."
    },
    {
      "prediction": "I'm not sure why this should be done here. I'm not sure if this is the case.",
      "reference": "I think this is ok for now. This ties into the larger issue of the site not having a consistent method for relaying form input errors. Please make sure the focus gets set on the close button when the dialog opens."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `GhostTable` and `SamplesGenerator` for calculations.",
      "reference": "Should these link be removed?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please make this a keyword-only argument by adding a `*` argument before `add_undo`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "didn't quite follow what this code block is doing."
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the right thing to do.",
      "reference": "this doesn't sound pretty... I would rather we have a proper navigation for all modes - AFAIK TV remote navigation is very similar to normal keyboard, but maybe it just uses another key codes - those should be extracted in a single file and defined there depending on context then"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `value` and `checked` properties.",
      "reference": "After diffing the children we check whether the value got out of sync, if it did we update it. We also update the `_prevValue` to prepare for the next event hitting our controlled component"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It provides a type called Node which is a fully functional bee client. This package is where the dependencies are injected. It is not just a glue-code, it is concept of node."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think this will change `''` to `'%'` unconditionally, i.e. there'll be no way to set `''` anymore. This should really only be used for values which make no sense anymore."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Nit: this table's row key map -> this table's row keys map"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this change should be reverted"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'm a bit confused about the `os.path.dirname(basedir)` here - is this just to get to the parent directory? Either way, I think I'd prefer just having this in `update_version.py` as it's not needed in qutebrowser itself."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Revert this change and see below why..."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Should not switch to `lvis_v1_instance` here because that base config uses ClassBalancedDataset to oversample the data."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is an informational message that allows someone to read the console output and understand how the grid node is configured. Please leave."
    },
    {
      "prediction": "I don't think it's a singleton alert.",
      "reference": "This doesn't make sense to me. What does RaiseSingleton mean? To me it sounds like a single object is being.. raised? Not sure."
    },
    {
      "prediction": "I don't think this should be used in tests.",
      "reference": "What's the benefit of having jobExecutorTests as a member variable? What do you think about making the method static? Afterall, it is a stateless method."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "This looks like it's only downloading things, not really checking their true validity. Especially for the MD object. Should we call `BareRootMetadata.IsValidAndSigned()` in `mdGet`?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Nikoli, I believe that this addresses your concern. One question for you or Jae-Seung is if any allocation from the clone is properly cleaned up when the vector is destroyed. I believe that it should."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "should be `ECSApp`  "
    },
    {
      "prediction": "I don't think this is the right thing to do with the `w3c` command.",
      "reference": "flake8 is going to fail on this having 2 lines"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "should we make a dir named controllers/scheduler/podchaos"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the key values.",
      "reference": "there seems to be one KeyNode in kubernetes.go of PV.. would it make sense to use it?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Im gonna be a little annoying here but did you configure your linter correctly? This empty line should not be here. Maybe go to settings and check if `goimports` is enabled?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Don't think this belongs in this pr"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "We can assert on the existence of Outbounds through ClientConfig calls right? Since this is only for tests, do we need this function?"
    },
    {
      "prediction": "I think this is a bug in MvvmCross.Core.ViewModels.",
      "reference": "@martijn00 so this PR introduces a new ViewModel lifecyle method? It isn't in the PR description/any new docs  "
    },
    {
      "prediction": "I don't think this is needed for the transformer_head, but it's not needed for the transformer_head.",
      "reference": "Are these modification duplicate? Or should we move it into base detector."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since this is private and single use it should be un-wrapped inside of the two-arg dagSeed method."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `t3lib_div::array_merge_recursive_overrule` and `t3lib_div::array_merge_recursive_overrule` and `t3lib_div::array_merge_recursive_overrule` and `t3lib_div::array_merge_recursive_overrule`",
      "reference": "why the order change? Also for the next chunk. (I understand the result will be the same though)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I wonder if this should just be a single `string`? We don't have any cases where we return different types and it would make the parser simpler to just read a single identifier."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I don't think this needs to change. Can you go back to the previous implementation?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Bump it 2 lines higher, 'c' > 'u'."
    },
    {
      "prediction": "I think this is a bug in vesoft-inc.com.",
      "reference": "Please do not add author here"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Similarly, we should be able to persist action uniformly"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `expires_in` method.",
      "reference": "I think i'd prefer this override to be in the test helper instead, if that's possible?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This would be better with context added via wrapping or fmt.errorf()"
    },
    {
      "prediction": "I don't know if the License is available.",
      "reference": "What's the purpose of this file?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "@bhariharan Why was passcode length requirement allowed to be lowered?"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "This file needs a license header, too. Sorry I didn't catch that earlier."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "probably don't need `[:]` why not reference into `github.com/algorand/go-algorand/daemon/algod/api/server/lib` here and skip bouncing off daemon/algod/server.go ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why reference is converted to table?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we implement pagination in the fake datastore so the server startup code that paginates entries for trust domain validation can be tested?"
    },
    {
      "prediction": "I don't think this is the case where `f.Vectorized` is nil.",
      "reference": "What mechanism will be exposed so the caller knows they're using the vectorized version?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we remove respond_to block its not required here"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Do not do that even in example, we demonstrate bad practice"
    },
    {
      "prediction": "I don't think this is the right thing to do with this, but I don't think this is the right thing to do with this, but I don't think this is the right thing to do.",
      "reference": "Hm, taking a second look over this, this is why we have the object inheritance structure that we do. This could be divided up by having a custom determine_if_x86_64 in the pswindows/exec hosts and then a default method in hosts.rb. That way all the custom ps windows work is in a single location."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We have to `.Complete` now because of empty/null string test cases."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Is there still a way to specify no recursion?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "How is this name being URI safe and being used programmatically related?"
    },
    {
      "prediction": "I'm not sure if this is the case for the first time, but I'm not sure if this is the case for the first time.",
      "reference": "I think we have to keep this as a fallback for now, else it's a small breaking change :("
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "nit: shouldn't be part of this PR."
    },
    {
      "prediction": "I think this should be an error, but it's not a problem.",
      "reference": "this change looks wrong to me. I think the test is trying to signal that something went wrong by throwing the `Error` here, otherwise the `catch` below will swallow it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm doubting if this should be `if (_layout.IsThreadAgnostic)`, as ThreadAgnostic stuff could be calculated on every thread. (and thus could be lazy). non-ThreadAgnostic should be calculated on the main thread."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please use only `Logger` instead of `org.slf4j.Logger`"
    },
    {
      "prediction": "I don't think this is the case where we don't want to republish the block.",
      "reference": "Should this be \"no limiter drop\", since this isn't an absolutely essential activity for the stability of the network?"
    },
    {
      "prediction": "I don't know why this is the case for the `deleteAccountAlias` command.",
      "reference": "I updated many of the success messages, because most of these operations don't return data if they succeed. This meant many of the operations would print: `Success null` if the script ran successfully."
    },
    {
      "prediction": "I don't think this is a bug in pyx.",
      "reference": "Could you simply add it to the previous clause ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "@joshyrobot, I think you can just use localeCompare with only the first argument and leave the other arguments out (here and all the other lines changed). It seems to do the right thing, and then we don't have to worry about these extra options."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@chengren311 : where does this logic move to?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Can we have a `nil` exception check at `s.scope.ManagedMachinePool`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Rather than deleting this, should you just reformat it so it's the `*` settings, so if nothing is configured in facets.ini, the existing default behavior continues to work?"
    },
    {
      "prediction": "I'm not sure if it's a string, but it's not a string.",
      "reference": "wrap, single line"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "always use brackets for if statements"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`NUnitIntegration` doesn't need to cache this anymore."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why did you change it to `>=` here?"
    },
    {
      "prediction": "How to do this?",
      "reference": "Looks like this needs to be updated. There is no need to remove `hadoop.` if Hadoop tables don't use this code path."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This require isn't need anymore, right?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "a bit weird to see payments crypto package inside connection manager. There probably will be services not having any relation with payments that will use connection manager. Thats why probably ping-ping by itself can be useful without any relation to payments.."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I like the overall idea here, but I wonder if it would be more clear to define the property in the trait, and then set it in the constructors of the classes using the trait. Alternatively, at a bare minimum, it may be a good idea to add `?? 'Bibliographic'` here, to account for the possibility of the trait being used in a class that does not define the property at all."
    },
    {
      "prediction": "I don't think this is the default for the max congestion window.",
      "reference": "I would prefer to not have a magic number, but construct this value out of other constants we already have."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "The limitation is if somebody configure another policy with the same name, but it is an edge case we can ignore I guess."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `gcpkms` module. I'm not sure if this is the right thing to do with the `gcpkms` module.",
      "reference": "? The package is named `hashivault`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I don't think this should enable xwayland, because it's convenient to toggle xwayland just by setting `xwayland` to `false`"
    },
    {
      "prediction": "I don't think this is a bug in k8s.io/client-go/util/keyutil.",
      "reference": "Remove this line by accident?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Calling `.stream()` on a `DomainObjectCollection` is pretty much always a bug, as it doesn't include objects added later (and encourages people to use afterEvaluate). I wonder if we should make this an error prone check?"
    },
    {
      "prediction": "I don't think this is a bug in ddev.gitignore.",
      "reference": "Thanks for paying attention to other places this might happen. This one is particularly important; I probably never should have gotten in the habit of CheckErr(), since it does a log.Panic() explicitly, which looks like something else until you look closely. It's supposed to be used places where \"can't happen\" but Things Can Happen."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "What is the different between nw_tos and ip_dscp? Only high 6 bits vs low 6 bits and supported version?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm assuming that asSmarts & cxSmiles == asSmarts"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Seems like an oversight but I don't think the super would do anything else in this case unless I'm mistaken."
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "Curious, do we consider this as pedantic for example code?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Should we convert the entity name to snake case using `Doctrine\\Common\\Inflector\\Inflector::tableize` or similar ? Should a `snaked_name` or whatever be part of the entity metadata in order to use it for form names, ids, & other html attributes ?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Should be `client.outboundIp`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Must these `using` statements not go inside the `namespace` block?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Why? I thought the previous way was idiomatic. (Same with the `MetadataVer` stuff above.)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `require([\"contentuploader\"], function(ContentUploader) { require([\"contentuploader\"], function(ContentUploader) { require([\"contentuploader\"], function(ContentUploader) { require([\"contentuploader\"], function(ContentUploader) { require([\"contentuploader\"], function(ContentUploader) { require([\"contentuploader\"], function(ContentUploader) {",
      "reference": "shouldn't we `reject` here instead?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "check err or use gasPriceUnitIOTX, _ := if we are sure action.Core.GasPrice is correct"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just curious, was wait not used at all before?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "nit: can we remove this?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "is it not a problem when one synchronized function is called by other?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "We (even as admins) shouldn't override the User Preference settings like `email_master`, `email_posts`, `email_kudos`, `email_new_followers`. These all would be set by the user of their choice. Please do remove these attributes from editing//updating. Thanks!"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "\"Este :attribute j est anexado.\" sounds better."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This line should be repeated for every module that needs testing. One cannot rely on nosetest to automatically discover all the modules. On the bright side, there is no need to change any of the other files."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "This error was unused"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Personally I wish we didn't have a proto for every single little thing we do. RequestShardAction with an enum for the action type would be a lot cleaner imo, but I'm pretty sure that ship has sailed :) Just kvetching."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Does this make more sense as `trails/_trail` now?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "synced offline. let's move this to `agent_unix.go` to make the IMDS call, since this is not supported in Windows."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `py_install` and `py_prep`?",
      "reference": "Too much indentation here. Should match the lines above, which have four spaces."
    },
    {
      "prediction": "I don't think this is the case for the CoreCH algorithm, but it's not the case for the MLD algorithm.",
      "reference": "Same here we still need this test to make sure the fallback works."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'm wondering if we can actually base this on a `IMvxPresentationAttribute` instead of the base one."
    },
    {
      "prediction": "I don't think this is a problem with the `parentVNode` and `parentVNode`",
      "reference": "could we switch to `undefined` here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "The cleanup call"
    },
    {
      "prediction": "How to do this? I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think \"View artist\" is a bit more standard and expected. Or even \"Go to artist\" to take the Spotify terminology as-is."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It might make sense to refactor this later so that we use a Bolt-native type to hide sensitive values."
    },
    {
      "prediction": "I don't think this is a test case, but it's not a test case.",
      "reference": "We were trying to move away from this to force people to always run tests under py.test."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "1 - create browser specific options class: - chromeoptions - firefoxoptions - argsoptions"
    },
    {
      "prediction": "I think this is a bug in S3, but it's a bug in S3.",
      "reference": "should be a case insensitive match though no? DOCTYPE and doctype are both widely used"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `account_id` parameter.",
      "reference": "We must have a `fail ParamNotFound` here for cases where `@account.nil?`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "How come this change was needed?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Why are there only 6 pins here, while below it appears to have 8 ADC inputs? Are pin 2 and 5 used for something else on this board?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we need an issue to track that chain sync omits BLS messages, and then to fix and test it!"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "what is this default about? I am not using ngrok atm so would prefer an env var."
    },
    {
      "prediction": "I'm not sure if this value is 'true' in production enviroments.",
      "reference": "@Samuell1 Might be better to say \"Automatically check for plugin updates on login\"."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Thanks for the additional Process helper! Can we also cache the first `Process.GetCurrentProcess()` result in a static field so we don't have to repeatedly call it? It means we would also need to dispose it when the static `_runtimeMetricsWriter` instance is disposed"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "just wondering what is the result of breaking the logic we test here? it seems that in that case we will just not return immediately, but i'm not sure whether the test will fail?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should fail the test if this returns `err != nil`."
    },
    {
      "prediction": "I don't think this is the case for the provision failed terminal.",
      "reference": "What is the drawback of not having this flag as a gating condition to report the metric?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`getProcessName()` will be less ambiguous, since Caddy has \"apps\" that it runs internally."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is there any way to not hardcode this given we know the size in bytes? The public API has the flexibility of being a Span. Should we maybe not do anything printing DML? The runtime allocates the buffer, but it's a \"scratch memory\" area, The delegate gets it passed in and they decide how to use it. Also, how is DML used if the feature is for macOS support?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How about just override the `buildFilter`? Passing another function here is a little weird."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should just be a `.Bool()` flag I think, we don't encode anything beyond y/n here. See `$(RUN_CHECK)` and `$(STOP_ON_PKG_FAIL)` for examples of how to pass those in."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this needed?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This code is passing a non localized string when it should be passing in a localized string or it should use the name of the item being deleted."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "how about moving it under L26"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this needs to be tested"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `:name` and `:description` and `:published?`",
      "reference": "Style/MutableConstant: Freeze mutable objects assigned to constants."
    },
    {
      "prediction": "I think this is a hack, but I think it's a bug in the JDK8252739.",
      "reference": "Just a thought, really. If it's a bug that can be probed for (and it can be - see Adrian's repro) then it could as well be a static initialization of a supplier of Deflater instances; if we probe for a buggy JVM, we return the wrapper. If we don't we return the Deflater. This way on non-affected JVMs nothing happens and if we do use the wrapper, we know the JVM is broken."
    },
    {
      "prediction": "I'm not sure why this is a realistic string?",
      "reference": "Looks like this should be publicly accessible for tests in any modules?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Allow putenv is necessary to be able to get environment variables with `getenv`?"
    },
    {
      "prediction": "I'm not sure if this is a leap year. I'm not sure if this is a leap year. I'm not sure if this is a leap year. I'm not sure if this is a leap year. I'm not sure if this is a leap year. I'm not sure if this is a leap year. I'm not sure if this is a leap year. I'm not sure if this is a leap year. I'm not sure if this is a leap year. I",
      "reference": "use function to check it. - don't do everything in main"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Sorry I'm confused. Why not kwarg this like the others?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `vex_W_extensions[2]`.",
      "reference": "First, any changes here should be synchronized with instr_compute_VSIB_index(). Second, the original looks correct to me: the first letter of the opcode name suffix is the index size, while the second is the memory size. So \"vpgatherdq\" is a d-sized index and q-sized memory. The operand size we store for memory accesses is always the memory size, not the address size, and for VSIB we store a single memory element size. It looks like we have no inside-opnd_t storage of the index size: that's done by dispatch on opcode it seems. I have a bunch of notes of discussions on how to handle VSIB: we decided to bail on encoding too much inside the opnd_t I guess."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `build_tracking_url` and `build_tracking_url` and `build_tracking_url`?",
      "reference": "Sorry for going back and forth. Adding docstring here would be very helpful for others to understand the need of this method."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You introduced a bug here."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Should we log a warning/error if only one is specified and not the other?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "`ctx` is unused in GetLatestEvent"
    },
    {
      "prediction": "I don't think this is the default port for the node.",
      "reference": "This looks good to me. Personally, I would have the following for maximum flexibility: * convert peering_port from uint64_t to int. * Set the default value to \"-1\" to specify the value is not set * if the value is -1 then do `config.node.peering_port = network_params.network.default_node_port` That would allow for 0 to mean, select the port number yourself and be more consistent. But I am happy with the change as is, as well."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "The blank line between the summary and detailed description is better to be kept."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Curiously, are these indents intended or should they be aligned?"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `roleText` attribute. I don't think it's the right thing to do with the `roleText` attribute. I don't think it's the right thing to do with the `roleText` attribute. I don't think it's the right thing to do with the `roleText` attribute. I don't think it's the right thing to do with the `roleText` attribute.",
      "reference": "What if we changed this to this? roleText=attrs.get('roleText', lambda:getSpeechTextForProperties(reason=reason,role=role)) That will prevent the function from ever needing called in the roletext case, and removes that if."
    },
    {
      "prediction": "I don't think the signal is being delivered after the detach.",
      "reference": "This will still result in a safe_read_tls_magic on AMD in tls_thread_preinit()."
    },
    {
      "prediction": "I think this should be the same.",
      "reference": "Can you remove this change?"
    },
    {
      "prediction": "I think this is a bug in the ACME spec.",
      "reference": "Oh, was that a bug in the validation?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please use the Google java code style. Basically, add more space characters like in the statements below. Next to method arguments and curly braces. This is currently not checked on CI because it is too inconsistent in the code base but I would prefer new code to be consistent."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Actually, I don't think we need to create object on heap."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is a file we copy from gRPC, sp ideally it be fixed upstream as well.."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "changes like this, just strangle guava usages to be replaced by DelayLimiter into one place"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "PropTypes need to be updated accordingly here. Note that the type also needs updating, not just the case. That is, these should both expect a `PropTypes.elementType` now instead of an `element`."
    },
    {
      "prediction": "I think this is a hack. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "maybe extra paren around `strncmp(...) != 0`"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "We should call `Windows.onResume `: - When the app is launched for the first time - When the app is resumed after being paused (home button and resume or device goes to sleep) - After a permission prompt is displayed"
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Rename to ForksSchedule? Maybe in separate PR."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why a blank line here?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I have a sense that this will actually eventually change to check the actual date so that subscriptions can be deactivated in the future. But I mention that here just to keep you in the loop. We should not make that change now, because it's not needed functionality."
    },
    {
      "prediction": "I don't think this is the default for positional params?",
      "reference": "What is the reasoning for using the negation of `isOption()` instead of simply using `isPositional()` to identify a positional param?"
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "Why would you add those if client version min is set to 1100?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "You can delete this, it will now need to live in `gointerfaces` package"
    },
    {
      "prediction": "I'm not sure why this is a partial?",
      "reference": "Okay, I still don't understand why you have to add `html_safe` here, and it still seems like a very bad idea. It will allow html tags in the title, and keep Rails from escaping literal greater-than or less-than chars not intended as HTML tags. It ought to work to just let Rails do HTML-escaing as normal, without any manual `html_safe` or `strip_tags` or whatever. I am not clear on what problem you are trying to solve, why the straightfoward approach does not work."
    },
    {
      "prediction": "I don't know why this is the right thing to do?",
      "reference": "What is is subject when it's not the email subject. Why are we having to do this crap? What's calling this with an empty string?"
    },
    {
      "prediction": "I think this is the default sampling probability.",
      "reference": "Could you also remove the `defaultSamplingProbability` constant from `sampling.go`? It seems to became unused with this change."
    },
    {
      "prediction": "I don't think this is a good idea to do with the `MergeLabelsAndAnnotations` and `MergeLabelsAndAnnotations` and `MergeLabelsAndAnnotations` and `MergeLabelsAndAnnotations` and `MergeLabelsAndAnnotations` and `MergeLabelsAndAnnotations` and `MergeLabelsAndAnnotations` and `MergeLabelsAndAnnotations` functions.",
      "reference": "can you delete the `generateDeploymentStrategicPatch` function as well?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd keep this at `info` level..."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Don't use DCHECK to debug your code if it's the regular branch you need to handle."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You should return null here instead. Null is an acceptable default value for the image attribute."
    },
    {
      "prediction": "I think this should be a `catch` statement.",
      "reference": "react bails as well?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "Can you please tell me why you did this?"
    },
    {
      "prediction": "I don't think this is the case for the `videoConstraints` property.",
      "reference": "Reading this again it should prob prefer the `videoConstraints.facingMode` value over `facingMode` if the former was already set"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "There's a good bit of class-level stuff that's repeated in our various product types. Think it's worth extracting a...dare I say it...module?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please do not modify the `config.Target` field, it should contain exactly what is extracted from the JSON files. Instead, you can either: * Add a getter to the `config` variable (`*compileopts.Config`), so you can simply call `config.WasmAbi()` to get the value. * Use a local variable instead. The getter would be slightly cleaner, as it matches the pattern of other configurations (`CGO_ENABLED`, `GC`, `NeedsStackObjects`, etc)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The nil check is not necessary for these. Append checks both sides for nil."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't we instead have the SDK apply these, internally? I.e., I would expect to see the dctx entries included in the span as first-class distributed correlations, not as span attributes."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "nit: rename this in proto and update impl to `Search` to avoid stutter"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the query builder.",
      "reference": "is it necessary to order by id as a second ordering? this will take place only when several new slider items are created without reordering (position is then null). Wouldn't be better to recalculate position after creating a new item? (right now items with null in position behave differently in administration and on frontend)"
    },
    {
      "prediction": "I don't think this is the same as the payload gas per byte.",
      "reference": "`ClaimFromRewardingFundBaseGas` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "How about modifying the NOGIL definition so that it only does anything if the thread safety flag (RDK_BUILD_THREADSAFE_SSS) is set?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "blockheighter would be more clear"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is so weird as a utility function."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why? What would happen if you did not?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Unrelated bugfix for NPE."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "What if some extended the `AdminController` and had a check for the old option name? Could that be a valid use case?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This will be only available when data-manager is enabled, is there a fallback in case data manager is disabled?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you think we want to move the call to `generateWorkerServiceRecommendedActions` inside `RecommandedActions()`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The VUIDs in this area are not great, but I think `ValidateQueryPoolStride` should probably be skipped if the query pool was created with type `VK_QUERY_TYPE_PERFORMANCE_QUERY`. VUID-02828 might be a better fit, but again, the existing VUIDs step on each other so it requires a bit of interpretation."
    },
    {
      "prediction": "I'm not sure if this is a Keccak key, but I'm not sure if this is a Keccak key.",
      "reference": "Iguess you should use ToDbKey here"
    },
    {
      "prediction": "I think this is a bug in the database.",
      "reference": "x.tbk is the \"index\" below, and is done in Start()"
    },
    {
      "prediction": "I don't know why this is the case.",
      "reference": "Do we already have a convention for this? If not, would we consider \"DataDog.IsAppInsights\". And then use \"DataDog.\" prefix for all this settings, environment variables etc..? Such settings are, essentially, public APIs because they may conflict with customer data. Regardless of that , AppInsights has an s at the end :)"
    },
    {
      "prediction": "I don't think this is the right thing to do with `time_key` and `log_key` and `time_key`?",
      "reference": "this assignment is not necessary if the offsetof() is used in the configmap"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I'd rather leave a TODO here at least."
    },
    {
      "prediction": "I think this should be the same as `test_body_is_transmitted_during_redirect`",
      "reference": "Shouldn't this be `resource`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why does this become blocking for the CPU path? Shouldn't it remain independent of the GPU path?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Do we need to change occurences where `setup` was called before?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is this TODO still valid? Or are we going to put this somewhere else later?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "We generally don't do parantheses in if conditions in Python. :) this could be better written as `if from_ts is None`"
    },
    {
      "prediction": "I don't think why this is needed?",
      "reference": "Odd that we'd set just element 299 of a 2000-byte buffer to null. But I see that this is the way it was before."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "ScoreFunc is not used in this PR. Maybe to add it later when needed?"
    },
    {
      "prediction": "I think this is a bug in the browser.",
      "reference": "super nit: I think this might be easier to read as `requestHeadersFromResponseWriter`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Need to include \"common/base/Base.h\" in front of this line"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `getElementSpec` and `getElementSpec`",
      "reference": "Changes in this file should go into a separate PR."
    },
    {
      "prediction": "I'm not sure if this is the case for a random token?",
      "reference": "Please ensure that this will not start putting single quotes where double quotes are expected."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`ProvideConfig` was changed, looks like it will not compile for windows, and should be changed too."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "This does not look right, you're listing all private repositories.."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "An OPTIONS request should respond from _any_ path? Seems weird to me..."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `show_filter` option.",
      "reference": "you need to add the content type"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need to distinguish between these two processes? I'm thinking maybe we can have a list of processes and treat them all equally."
    },
    {
      "prediction": "I think this is a bit of a hack, but I think it's a bit of a hack, but I think it's a bit of a hack.",
      "reference": "This is used only for out-of-line -- so yes this seems right to do for x64. Inlined is aligned separately at the end of prepare_for_clean_call(). There the ifdef is x86_64 or MACOS -- no ARM, why not? Also, please add || MACOS here to match the inlined."
    },
    {
      "prediction": "I think this is a bug in MySQL, but it's a bug in MySQL, but it's a bug in MySQL.",
      "reference": "guess I'm wondering if this needs to be refactored to use Schema.joinCondition() or similar?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `exec_manual_tests` option.",
      "reference": "Does it make sense to restrict this option to `exec` only? You could add it specific to that subcommand using the `method_option`...method. There's an example of it for hosts in the `init` function."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is very expensive (lots of allocations, lots of data copying). Could we do something like check IndexOf('%') and bypass if no hit?"
    },
    {
      "prediction": "I don't think this is the case where the world type is not a PvpWorld, but it's not a PvpWorld, but it's a PvpWorld, but it's not a PvpWorld, but it's a PvpWorld, so it's not a PvpWorld, so it's a PvpWorld.",
      "reference": "This should be `WorldType.isDeadmanWorld(client.getWorldType())` to be inline with the other WorldType calls."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "do we also need to change `mlvl_confid` -> `mlvl_confidences`>"
    },
    {
      "prediction": "I think this should be a string, not a string, not a string, but it's a string, not a string, but it's a string, but it's not a string, but it's a string, but it's not a string, but it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "I feel slightly that InterfaceExclude is not a clear name - bearing in mind that our config names are, to some extent, an external API. From an external point of view, a clearer name might be IPVSInterfaces. Then it would obviously make sense for the value to be something like 'kube-ipvs0', and it would be a matter of Felix's internal implementation that we choose to exclude those interfaces from our monitoring. Alternatively, if we want to keep this at a level that is more general than just IPVS, perhaps 'UnmonitoredInterfaces'? WDYT?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "This should be `re.search` with a `^` anchor added to the regex, as what we want here is really any path starting with something like `E:`."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "Since `IsKubernetesBuiltInResource` at L69 returns false due to lack `networking.istio.io/v1alpha3` in `builtInApiVersions` within `pkg/app/piped/cloudprovider/kubernetes/resourcekey.go`, it will never reach this point."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does codecov not run this test? Not sure how else it would not be covered."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "can we add some sample of JSON_DATA format in the usage?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Using `Tracer.Instance` in here is problematic for testing   It will likely cause some other tests to break I think - that's why we started passing in `IScopeManager` EDIT: I see you used `[TracerRestore]` - maybe that'll be enough!"
    },
    {
      "prediction": "This is a hack.",
      "reference": "make all of these `static final` fields UPPER_SNAKE - they are constants."
    },
    {
      "prediction": "I don't think this is a DoT, but it's a DoT Shielding.",
      "reference": "No possible chance for weird overflows here, right?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Or we could use a Float object to more clearly show as user-settable via non-null?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "finalizedHeader should be saved in FinalizationManager when we have FinalizationBlockHash != Keccak.Zero"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not using ExactName: true would remove the need for manually adding workflow ID as it would be added automatically by Daisy. E.g. 'disk-importer-2-import-ovf-7mn7h' was created from diskImporterDiskName above even though only 'disk-importer-2' was specified. ExactName: true should be used for resources that shouldn't include any temp prefix/suffix, such as disks that will be permanently attached to a created instance. Scratch disk is not one of them."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "If we support multi-index column later, we need to rename to fit the pandas' requirement."
    },
    {
      "prediction": "I'm not sure if this is a JSONValue, but it's not a JSONValue.",
      "reference": "I'm not sure this is really needed. JSONValue type can be used the same as a map as far as operators go, including range. I'd leave this out for now unless there is a strong reason to keep it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "sorry for nitpicking but I would love a new line under this line"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "ChannelImplementation field naming is not clear, is it some kind of standard? Maybe it can be named ChannelID?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Looks like there is a typo: `expireSnapshots` -> `removeFiles` or whatever name we go with."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Thanks for looking into this. I think it looks a bit strange to have this check inside the for loop. Wouldn't it also work to initialize `idxCurrentSort` with 0 instead?"
    },
    {
      "prediction": "I don't think this is the right thing to do with it.",
      "reference": "Just a small ordering thing: Could you please bring `IMPORTANCE_HIGH` to the bottom and maybe even have one line between it and the Notification IDs?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Should this be boost logged?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "What is the reason for doing expunge here? This method is purely for converting the timestamp."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This calls sanitize twice if the name isn't valid."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is there an equivalent that'd allow zero or one?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is it possible to update/re-evaluate entire metatask object for every repeat? If we decide/need to use a repeatWith resources in let us say labelSelector(bad example) then we would have to add another logic to update those properties."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "unnecessary conversion (from `unconvert`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "typo in commit message `openening`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `adios2/engine/hdf5/HDF5ReaderP.h` or `adios2/engine/hdf5/HDF5ReaderP.h`?",
      "reference": "User-code doesn't see the internal ADIOS headers anymore. This whole include block should just be `#include <adios2.h>`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: I guess we can omit this (unless you had a reason to specify it)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is Hub public?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why is this deleted?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Maybe move that into a partial"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Error return value of `dao.Stop` is not checked (from `errcheck`)"
    },
    {
      "prediction": "I think this is a bug in cobra.",
      "reference": "util.Warning()? Easier to say."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "this default is kinda superfluous (although i see it was already there before PR )"
    },
    {
      "prediction": "I'm not sure why this is a `Node`?",
      "reference": "How is this related?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I'm breaking one of the rules here, it feels like the right thing to do. Open to alternative suggestions."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `if` statement.",
      "reference": "The use of `#should` was triggering an rspec depracation warning for me, which is why I switched this to the rspec 3 style."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Why are you setting the CacheChange as REQUESTED when it is not valid (it was erased from history)?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `isEmpty`?",
      "reference": "`lodash` shouldn't be grouped under WordPress dependencies"
    },
    {
      "prediction": "I'm not sure why this is a class, but it's not a class.",
      "reference": "This needs to be public so that Avro can call it."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `apiFetch` function.",
      "reference": "`Google*` shouldn't be under External dependencies - seems like ESlint is not properly recognizing that these are aliases to internal dependencies."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think he meant the docstring in this constructor. yea we should fix"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "so .. this basically follows the pattern from JapaneseTokenizer, I think. .. but somehow I don't see where we defined ResourceScheme? We're not referencing the one in kuromoji, right?"
    },
    {
      "prediction": "I don't think this is the right thing to do with this, but I don't think it's the right thing to do.",
      "reference": "It would probably be better to do: const SecurityProtocolType Tls13 = (SecurityProtocolType)12288"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do, but I'm not sure why this is the right thing to do, but I'm not sure why this is the right thing to do.",
      "reference": "Similar to the above, put this setting back but keep the value as `'{}'`"
    },
    {
      "prediction": "This is a hack.",
      "reference": "As discussed in chat - we should run this function within an app context which means that we'd already have a logger configured, and a connection to timescale set up"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'm curious about why this needed to be removed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "why did you remove `zip`? It is used!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is there any reason that we don't add a similar condition like `ChannelConditionTopic` to the channel?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "before php8 \"goto\" was a reserved word and was not allowed as part of the namespace. Now test checks for validity of plugin namespace according to PSR-4"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: I'm not sure it can be addressed in this diff, but it seems odd that NewOutbound supports TLS but NewSingleOutbound does not. As a somewhat naive user I would expect the only difference between these two APIs is how peers are chosen."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would advise to enhance the test for the method `CallOneway` - we should have a test very similar to `TestCallSuccess`. We should test: - Success with response (even if it is callOneway) - Success with no response and empty payload - Errors"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We're already matching +. Not sure why this changed."
    },
    {
      "prediction": "I don't know how to set the service name here?",
      "reference": "Please add line breaks, so the line doesn't exceed 80 chars."
    },
    {
      "prediction": "I'm not sure if this is the case where the `options` is set to `null` and `null` are not allowed.",
      "reference": "I initially thought (inccoreclty) this is a breaking change! The public api analyzer is a gift!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure how this one didn't segfault before."
    },
    {
      "prediction": "I don't think this is the default value for `trueOrFalse` and `falseOrFalse`?",
      "reference": "Same points as in other test file."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Did you run gradlew tidy? Wildcard imports shouldn't be there, hence the question."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do, but it would be better to use the `status_finder` instead of the `status_finder` instead of `trail_with_progress` instead of `trail_with_progress` instead of `trail_with_progress` instead of `trail_with_progress` instead of `trail_with_progress` instead of `trail_with_progress.status_finder`",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is this going to restrict the output to *ONLY* ports that are bound to vfio-pci? That's not what we discussed yesterday."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Intention is to do the lookup here, I believe (where we can cache it). This would make the call non-pure function though. I'll confirm with lotus. ID addresses are the *only* addresses I expect to actually see here."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `emrfs` command, but it's not the right thing to do with the `emrfs` command, but it's not the right thing to do with the `emrfs` command, but it's not the right thing to do with the `emrfs` command.",
      "reference": "electronic medical record file system (EMRFS)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Put this higher in the list, like after \"bind\", since I guess we're considering the max request body size to be kind of a native/fundamental feature, built directly into the vhosts."
    },
    {
      "prediction": "I think this is a bug in Sonm.Hub.",
      "reference": "oh come on :("
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is an incorrect change. The dialect spoken is an important part of the handshake and should be communicated to users."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Remove as this is not needed anymore."
    },
    {
      "prediction": "I don't think this is the right thing to do, but it's not the right thing to do.",
      "reference": "This new class is for checking that #4551 works correctly with PlantUML output too."
    },
    {
      "prediction": "I don't think this is the default value for the key encipherment, but it's not the default value for the key encipherment, but it's not the default value for the key encipherment, but it's the default value for the key encipherment.",
      "reference": "Will this cause all certificates to be re-issued?"
    },
    {
      "prediction": "Should we remove this?",
      "reference": "I think tmp is also leaked at the end of this loop if no error cases are encountered."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The previous version didn't use `keyProjection` because the entire key must be projected. If the key is a struct of multiple columns, then projecting a subset of those columns can easily introduce key collisions that aren't in the original data."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not use StatusOr ? We can't ensure spaceId is greater than zero, especially when AdHocSchemaManager is used."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `github.com/chaos-mesh/chaos-mesh/pkg/chaosdaemon/pb` package.",
      "reference": "Does it seem we only use that as the json-rpc client? Do we have any other choice? It's a little weird."
    },
    {
      "prediction": "I don't think this is the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing to do with the right thing.",
      "reference": "Could you split this into multiple lines?"
    },
    {
      "prediction": "I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future.",
      "reference": "Doesn't the snapshot ID start off as null? It seems like we don't need to set it here."
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a better way to do this.",
      "reference": "I wondered why `buffer` was passed into `LookupPath`. What is happening here? Is `buffer[:0]` equivalent to `[]V4TrieEntry{}`, and hence `buffer` isn't needed any more?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: Ideally we would would use this abstraction everywhere we need this translation. I believe it's needed in the mining worker and the storage and market connectors."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "need to fix the error message here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Unsure of how to handle this one."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Will this.flowFinished verify with every finished state stated in Status.isStatusFinished method? If so, no need to verify isKilled."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "replace \"Child Workflow\" with \"any workflow\""
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Instead of showing the words \"symbolic link\" under the \"Size\" column, how about we introduce new icons for symbolic link to file and symbolic link to directory?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I",
      "reference": "Please add back the description of the parameter"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the tree root.",
      "reference": "Superfluous space inserted."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Didn't fix the problem. `href=\"\"` for SVG will still result in `undefined` getting returned by this function."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This seems like a strange change ... I wouldn't think that a change to access tags in the profiles would result in different bearings in this tests?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "As isCaret is False by default, explicitly specifying isCaret=False here is not needed, and is perhaps a little confusing. I'd prefer that anywhere in the codebase that isCaret is only ever specified if it needs to be set to true. Mirroring that of isFocus for setNavigatorObject."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We can't freeze this and then add something to it in the next line. The `freeze` on line 43 is sufficient. If Rubocop flags this we need to exclude it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not put two other routes after this line (221)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If FLAGS_meta_server_addrs is not empty, in which case \"toHosts\" return empty array?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "There is a function to output a \"JSONBool\" string. That would be a good start for finding uses. But maybe just have a look at where we decide whether it is a numerical or not, thus wrapping quotes around its value. Then you have it all I guess."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "oops, it should be `data._scol` so that it respects the expression stored in Series. Let me fix it quick."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Thanks for moving this up with the rest of the variables. Much tidier :)"
    },
    {
      "prediction": "I'm not sure if this is the case for the alpha release.",
      "reference": "I think `Rate` is a more precise and concise term for `PaymentPerTime`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this should maybe be: var limit = input.IndexOfAny(new[] { '+', '-', ']' }, **posNext**); You pretty much want to ignore any sign that is before the \"M\". But, if there is a sign somewhere before the M, and also after the M, you'd want to be able to find the sign after the M, right?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "if `checkStockNotEmpty` returns a reponse, you must return it or your script will continue its execution."
    },
    {
      "prediction": "I don't think this is a bug in the k8s.io/api/core/v1.",
      "reference": "Any specific reason for this change? klog should work correctly here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "we don't mention `last_modified` here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "same deal about the global state maybe interfering as in ActionBrowseTagline"
    },
    {
      "prediction": "I think this is a bug in Nethermind.Core.Test.Caching.",
      "reference": "so sweet to see a test as the first thing"
    },
    {
      "prediction": "This is a hack.",
      "reference": "usually when HTTP_PROXY=\"\" (empty), proxy should be disabled. could you set it to NULL when it's empty string?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `width` and `height` properties.",
      "reference": "Can you throw an exception if width or height are both null"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "This is a breaking change. I guess these might have been intentionally exported."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I don't think this is necessary. When options are used to set the split size in the Spark reader, it uses `TableProperties.SPLIT_SIZE` to pass it here. That should work for metadata tables as well, right? The situation that we need to handle in this PR is setting the default, like you had before. We just want to use a metadata split size so you can set it and not have the same split size used (by default) for both metadata and data scans."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it's not a problem.",
      "reference": "wait a sec, shouldn't this be `'*'`?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "It think you'll want the var for GMI import as well: daisy_workflows/ovf_import/create_gmi.wf.json (Unfortunately there's duplication between the two :/ )"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `get_context` and `set_context` commands.",
      "reference": "Nit: Group this with the other commands by moving it down one line."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would like to emphasize that a user can use non-vectorized reads to handle this file so maybe something like \"Cannot perform a vectorized read of ParquetV2 File with encoding %s, disable vectorized reading with $param to read this table/file\""
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the parameter name?",
      "reference": "Maybe add `positional=False`. It does not need it more than the other parameters, but one must start somewhere."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "Since we're here, can we use a template?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "saw you're also doing this in `test_types.py`: `spark = _spark_context()['test'].resources['spark'].resource_fn(None)` since `_spark_context()` uses `spark_session_local` won't the above break the tests?"
    },
    {
      "prediction": "I think this should be an error, but it's not a problem.",
      "reference": "`has(default)` i think is the preferred way of doing this"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "always put a space after a comma"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "@angmas1 move the else up, next to the closing bracket of the if block. Also, there is no need for the braces as your else statement contains only a single line. Make your if-else block similar to the block in lines 277-280."
    },
    {
      "prediction": "This is a hack.",
      "reference": "@AutomatedTester @davehunt thoughts on a new keyword argument?"
    },
    {
      "prediction": "I think this should be a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string.",
      "reference": "This change shouldn't be necessary for this PR. Please remove it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This variable is mostly unused, how about we make `NewTestCtx` return a pointer?"
    },
    {
      "prediction": "I don't think this is a bug in k8s.io/klog/v2.",
      "reference": "What is the basis of this value?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Nit: was this extra blank line added intentionally?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "nit: inconsistent spacing around ="
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `Sonata\\ClassificationBundle\\Model\\CategoryInterface`?",
      "reference": "We still need this import"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "We are pulling this because we removed \"groupID\" state and put it into the strategy implementations"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Is this file actually related to PCA?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "See above, this should probably remain `isFirstAdmin`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why the change to make it public? The expression interface has the `TypeOf` method?"
    },
    {
      "prediction": "I think this is a bug in NLog.UnitTests.Targets.Targets.Single_Archive_File_Rolls_Correctly. This is a bug in NLog.UnitTests.Targets.Targets.Single_Archive_File_Rolls_Correctly. This is a bug in NLog.UnitTests.Targets.Targets.Single_Archive_File_Rolls_Correctly.",
      "reference": "don't mind the snake cases in the test names. If there are in the test cases, it's fine IMO"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "`Id` defines REST resource address and should not be in payload"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `--class_wise` option.",
      "reference": "We can omit the underscore and just use `classwise`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Why not throw an exception instead then?"
    },
    {
      "prediction": "I think this is a bit of a hack, but I'm not sure if this is a data task.",
      "reference": "Looks like this doesn't need to change. Can you revert this?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "please import it like `from kinto.config import template`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `isIsolationFilterOpen` property?",
      "reference": "There are lots of default value changed, not sure if it break the old behavior."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "parameter should be called removeFromStaticNodes"
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "The handler will have an extra property in the marker to signal the implementation is in the provider, for the cases we want to add functionality, for example, custom implementations not in moto."
    },
    {
      "prediction": "I don't think this is the right thing to do with `deactivated_on` and `activate_on` and `deactivated_on`?",
      "reference": "Is this method actually being used anywhere? If not, I think we should remove it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Thanks! I somehow lost this between my far too many branchs."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `RemoteWebDriver` and `RemoteWebDriver`",
      "reference": "i think this should get put into its own file. This could start to grow :)"
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the case.",
      "reference": "Can you add a TODO for loading the tarball of the pause image into Docker?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Is there any value in setting the process to null like this?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This could be a good time to add a check that the prediction and target dimensions (except channel) agree?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "The requirement that OP_isb is bb-final needs to be a rule for clients, just like the rule that syscalls and interrupts must be bb-final: i.e., please add it to the dr_register_bb_event() docs."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The translate library has a method to replace the variables."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i don't think this test case is correct. in both cases inpalce=True returns nothing. We need to compare the ks. Also we probably need to make a copy of it. Otherwise you pollute the following \"ks\" because ks has been changed."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Any proposals how to make the naming somehow include the \"completed\" idea of this hook? `TlsHandshakeCompletedHook` or similar? Or using the `...Start/End...` scheme?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "it introduces a lot of complexity to the state, can we flush straightaway or create a two level flush store where the questions are read form unflushed data?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "There are two calls to getUrlFromRouteCache, but you're only urlencoding one of them. Is that intentional? Would it make more sense to do the url-encoding inside the getUrlFromRouteCache function?"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `getEditorInstance(editorClass, this.instance)` instead of `getEditorInstance(editorClass, this.instance)`",
      "reference": "Maybe we can use `this.instance.getCell` with `topMost` flag to get `TD` element?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Change this to Debug Level"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I refactored the Aggregate, those are hard to read"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This is now done in the after method, so this test won't pass any more."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What was the point of creating `user_block` if you're then not going to use it ;-)"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "@ueshin, I thought we can remove this entire file. Does that require some more works?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Just `return tokens.string[1:-1]` is enough"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "1 trailing blank lines detected."
    },
    {
      "prediction": "I'm not sure why this.getStyleClass().add(\"leftButton\"); I'm not sure why this.setPrefWidth(Double.MAX_VALUE); I'm not sure why this.setMaxWidth(Double.MAX_VALUE); I'm not sure why this.setPrefWidth(Double.MAX_VALUE); I'm not sure why this.setMaxWidth(Double.MAX_VALUE); I'm not sure why this.setMaxWidth(Double.MAX",
      "reference": "Isn't this the default max width? In any case I would prefer to see these definitions in the css files."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this thread-safe? (If not, and if the solution is to introduce locking, let's reconsider how we do the scheme changing instead...)"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Looks like this file has tabs instead of spaces."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hmm should we clean up container resources before task resources here? or the order does not really matter here?"
    },
    {
      "prediction": "I don't know how to clean old downloads?",
      "reference": "Please undo this :wink:"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `client_id` and `client_secret`?",
      "reference": "thanks for adding this missing association"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should I remove this in favor of the HttpsConnectionFilterOptions overload?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This shode be nullable, there alway sholud be at least one status in system , if not exist that mean data problme"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Spaces not tabs"
    },
    {
      "prediction": "I think this is a bug in Node v8.",
      "reference": "To get the files inside a directory, please use `readDirStats()`."
    },
    {
      "prediction": "I don't think this is the case for the `docker` and `plz` container.",
      "reference": "might be worth to call these `Isolation` instead of containers here and when presented to the user -- docker/rkt , in addition to cgroups and namespaces, also provide image discovery and filesystem preparation; there's also the security context and probably 1-2 other small things"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "File is empty, consider removing?"
    },
    {
      "prediction": "I don't think why this is needed?",
      "reference": "This seems to return the registry_url. The more meaningful URL is the catalog URL, which is the URL the user specifies in `quilt3.login`. The username might also be as useful here if not more useful."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Was the addition of `GasPriceOracleAddress` here erroneous?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `host_tags             ` option.",
      "reference": "I believe that you are going to have to do some work here to get the env var support for these values to still work correctly, otherwise they will get stored as :department instead of host_tags[:department]."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How was this causing the exception?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I still have issues with it loading Simplified Chinese by default over Japanese, since they also share characters and we're not sure if characters are different or not. As-is, this fixes Traditional Chinese and Simplified Chinese, but we're not sure if it'd still screw up Japanese text or not. I maintain that, in my opinion, Japanese should be the only script of this kind loaded by default (Because of Hiragana and Katakana, that aren't shared with any other script) and either variant of Chinese should be loaded only in their respective case."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "Isn't it better to stub AtomatonQuery and yield it here. IIRC it resolves simplest MTQ highlighting cases as nobrainer."
    },
    {
      "prediction": "I don't think this is the best way to do this, but it's not the best way to do this.",
      "reference": "Line is too long. [96/80]"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "My only concern with changing the node selector here is that someone else _could_ have built their own images for other platforms and set them to be used using the flag override on the controller, which in turn this change would break. Perhaps not changing the selector for acmesolver pods makes most sense, and then working on actually having support for Windows? wdyt?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Why do we need interface `InnerObjectWithSelector`, I searched the usage with this field, it seems nowhere use `GetSelectorSpecs()` methods provided by `InnerObjectWithSelector`"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Do we need this `init` here? We have already called the `InitContext` in `StartModule` directly."
    },
    {
      "prediction": "I don't think we want to use `self.execute(Command.W3C_MINIMIZE_WINDOW)` instead of `self.execute(Command.W3C_MINIMIZE_WINDOW`)`.",
      "reference": "This `if` is not necessary"
    },
    {
      "prediction": "I don't think this is a problem with `newProps.value` and `newProps.checked`?",
      "reference": "should we add a `mangle.json` mapping for this? We could reuse a property name that's only used on component or vnode objects right now, like `__s` (\"next state\")."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please update the yard docs to indicate this new option."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Can you provide an example in the godoc section on how to use this? From the implementation it looks like the AvailabilityZone field is required for example, otherwise it can fail / error, is that correct?"
    },
    {
      "prediction": "I think this is a bug in gorm.",
      "reference": "It would be great if this could be captured by a test."
    },
    {
      "prediction": "I think this should be the case.",
      "reference": "1000 -> 100 maybe too much, 200 ish to 500ish maybe a good option"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Any reason we need to keep this package's `ChecksumAddress` type or can we get rid of it too?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Above the one that was picked was the Button* prefix, and here it's the Header* prefix. Maybe the Button prefix is more general."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "I might prefer changing: public Block FindPendingBlock() => FindBlock(PendingHash, BlockTreeLookupOptions.None); public BlockHeader FindPendingHeader() => FindHeader(PendingHash, BlockTreeLookupOptions.None); in IBlockFinder, what do you think?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is necessary due to a bug in 4.7. Follow HIVE-1561 for getting rid of it."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with_options(through: :classifications, source: :classifiable) is the right thing to do with_options(through: :classifications, source: :classifiable) is the right thing to do with_options(through: :classifications, source: :classifiable) is the right thing to do with_options(through: :classifications, source: :classifiable)",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Some day (tm) I will also get rid of that one. But today is not that day..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Add a space between if and opening parenthesis please (i.e. `if (`)"
    },
    {
      "prediction": "I don't think this is the case for the `inplace` flag.",
      "reference": "nit: `rename` instead of `alias`?"
    },
    {
      "prediction": "I don't think this is the case for the root device.",
      "reference": "Per AWS docs EC instances have the root mounted at /dev/sda1. This label should be skipped."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I'm not sure it is a better way to address lose message, if wait here, edge controller cant process message, event from watching api-server will be lost yet, right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please keep the correct alignment, it seems broken now (at least in Github). Can you reverse the test (`if p.value_size is None`)? Also, do you want `6` when `p.value_size is None` or `x + 6`? Maybe, in that case, something like `lambda p, x: x + 6 + (0 if p.value_size is None else p.value_size)` would be easier to read. Or even easier: `lambda p, x: x + 6 + (p.value_size or 0)`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we make sure ECS service treats it as int64 as well?"
    },
    {
      "prediction": "I don't think this is the right-to-left indicator, but it's not the right-to-left indicator.",
      "reference": "Please follow the naming convention for variables, i.e. `windowText`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "alias can be `cast`"
    },
    {
      "prediction": "I think this is a bug in h2o.js.",
      "reference": "Let's use `%zu` instead of casting to `uint64_t` and using `PRIu64`. The alternative is to change the type of `mmap_errors` to `uint64_t`, though I'd prefer not doing that because some 32-bit platforms might not provide atomic operation support for `uint64_t`."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I recall there being a reason we had this one set only to suggeation. @carterkozak do you remember why? or is my memory getting corrupted?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should now be made into `if (it->second.empty())` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need to worry about a race condition on this decrement (@The-Compiler)? I'm not sure how the python callbacks work, so this might not need to be something to worry about."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should these assert that the extracted `SpanContext` is remote?"
    },
    {
      "prediction": "I think this is not allowed for RPN and single stage detectors, but it is not allowed for single stage detectors.",
      "reference": "typo: allow low quality matches."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "At some point we need to condense down and refactor our \"configs\" as we have too many in too many places and we're starting to get more illegible code. No change necessary but calling out for future reference."
    },
    {
      "prediction": "I'm not sure if aria_hidden is set to true.",
      "reference": "Can we add the `if label` conditional to this please?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@thunterdb, can we increase the minimal version to almost the latest ones? I was thinking people will mostly use the latest version of mlflow"
    },
    {
      "prediction": "I think this should be a `beforeAutofill` hook, but it's not a `afterAutofill` hook.",
      "reference": "If the last argument is going to be removed, why would we add it to the API docs? Shouldn't it be private for internal use?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "`Intermediates` or `Intermediate`"
    },
    {
      "prediction": "This is a hack.",
      "reference": "This is not the right exception class. There is an InvalidSelectorException class that covers bad locators."
    },
    {
      "prediction": "I think this is the only way to do this.",
      "reference": "If this code isn't needed, it should be removed."
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "Should the `doRequest` func be a method on the `connection` type instead of passing state from the type?"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string.",
      "reference": "we'll probably tackle these e2e tests at the end"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "what is this address pointing to? what are we measuring here? I want to have a better understanding."
    },
    {
      "prediction": "I don't think this is a problem with the `dep_status` parameter.",
      "reference": "Would it be better to pass the dependency status as the parameter into the SQL string? In case the enum value is changed in the future, we don't need to change the code here."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Hah I had `gorename` failing without this too."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "maybe prefix these with `appsec_` for consistency?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: this should be down further with the other github imports"
    },
    {
      "prediction": "I think this is a bug in NVDA.",
      "reference": "Why is this change necessary or related to the rest of the PR?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Hm, I wonder if the `see:` prefix is even necessary?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This should be translated."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I originally had this PR only changing the R package, but then ran into this error > Error: [LightGBM] [Fatal] Cannot change metric during training This is thrown even if you aren't actually CHANGING `metric`. I think the change here in `c_api` is closer to the desired behavior, only throwing an error if the parameter is being changed."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "These changes are just to make cli_spec a little more readable for VS Code users, as there's a bug with the Ruby plugin's syntax highlighting when you use multi-line regex literals."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't the global pull secret by in the namespace of the hive-operator? It is part of the operand."
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "kinesis-mock applies KINESIS_LATENCY to RegisterStreamConsumer actions so I added a sleep here."
    },
    {
      "prediction": "I think this is a bug in nebula.meta.MetaVersionMan.updateMetaV1ToV2(engine, nebula::meta::MetaVersion::V2); I think this is a bug in nebula.meta.MetaVersionMan.setMetaVersionToKV(engine, nebula::meta::MetaVersion::V3);",
      "reference": "Only V1 or V3 is return from `getMetaVersionFromKV`. So where do we call `updateMetaV2ToV3`?"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think this is a good idea.",
      "reference": "I think that V0 is missing here, which will prevent plugins that haven't been converted to work."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `withBundleAnalyzer` function.",
      "reference": "Should we remove this?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `docker` package.",
      "reference": "Put on top of the import."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "See above, this shouldn't be added."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "This'll likely get fixed upstream, we should let them deal with it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Somehow, this field does not seems useful for the exposed package api, only for the tests. Would you consider having an unexported field in `hostFactory func(context.Context, ...libp2p.Option) (host.Host, error)` instead to be set only by a new helper function defined in export_test.go. This is just a suggestion, not a hard requirement for the PR approval."
    },
    {
      "prediction": "I don't think we want to do this in the future?",
      "reference": "As a first argument to these function, please pass the date that should go forward/backward. Also please clarify what is \"n\" (possible values, unit) and what is timeDuration (possible values, unit, as from your code it seems to be \"day\", \"hours\", etc. but from your example it seems to be milliseconds)."
    },
    {
      "prediction": "I don't think this is a bug in Foobar2000.",
      "reference": "Are you sure you really need this code here? that script will be certainly run in NVDA's main thread, and core would have already called setLanguage."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why is this changed ?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Should this be \"the new revision value\"?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You have deleted :attribute"
    },
    {
      "prediction": "The \"License\" is not included in this file.",
      "reference": "The license header should be updated to the Apache one."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@zacharycmontoya Is there any way to distinguish a `SocketHttpHandler` from another `HttpMessageHandler` request?"
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "Not sure about this one -- did you check somehow?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Is there a good reason to keep this at the `pe_ver_win` name now that it's per-host?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Not in the order of display : Front, Ingredient, Nutrition here (which is the right thing), Actually displayed: Front, Nutrition, Ingredients"
    },
    {
      "prediction": "The `startTime` parameter is optional.",
      "reference": "Why delete `StartTime`? This `StartTime` was used to avoid the PID was reused."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "My concern here, is that if the dump_puppet_log also throws then we will lose the data about the teardown_exception."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should it be `int64_t`?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "is this value related to something ?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Add names to tuple elements ValueTask<(Keccak? Hash, AddTxResult? AddResult)>, should they both be nullable?"
    },
    {
      "prediction": "I don't think this is the case format.",
      "reference": "I think it might make more sense to do this in Name.upperCamel; it is the entry point for upper camel strings."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Huh? The point is that a cast isn't necessary"
    },
    {
      "prediction": "I don't think this is the default value for the environment variable.",
      "reference": "can we name it like `InstallV1Alpha1CRDs` ?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I need something to match when creating selectorsyncsets so added this label."
    },
    {
      "prediction": "I think this is a bug in RSpec.",
      "reference": "Isn't `nil` the default return value from an empty `rescue` clause? If that's correct, then we could just remove the `nil` line entirely as it doesn't serve a purpose."
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "Simple Storage **Service**"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Wouldn't that cause the obsolete indexes to be downloaded over and over again? After all these are still stored in the repository."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `params` hash, so we don't need to use `params.keys` here.",
      "reference": "We might want to move this logic to a Plain Old Ruby Object down the road. Not a blocker."
    },
    {
      "prediction": "I'm not sure if this.toolbox_ is not null",
      "reference": "move `this.toolbox_.position();` to just after line 1477. Context: the if statement on line 1472 checks whether this is a toolbox with categories, and if so it populates the toolbox. Positioning the toolbox is a reasonable followup to that, and means you don't need an extra if. You may also need to call `this.flyout_.position()` after line 1483, which is the equivalent for the non-category toolbox."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should the function above be .FirstOrDefault() instead? Otherwise, why check for null and tell ReSharper to ignore the fact that it can never be null?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `require('../jobs/job').STATUS_MAP` instead of `require('../jobs/job').STATUS_MAP`, but it's a good idea to use `require('../jobs/job').STATUS_MAP` instead of `require('../jobs/job').STATUS_MAP` instead of `require('../jobs/job').STATUS_MAP`",
      "reference": "Let's not create new connection, but rather user `common.db` one"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Can this use asset_path rather than defining an image_url helper?"
    },
    {
      "prediction": "I'm not sure why this is a function, but I'm not sure why this is a function, but I'm not sure why this is a function.",
      "reference": "Hindley-Milner signatures don't use literal types. They explusively use types. It's deal with that"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Could we just extend PolicyRule with more fields? It was originally designed as the struct required by openflow client, nested structs seem not helping. And for the name of the fields, initialism should be uppercase, OFID and NPName doesn't look good, then maybe FlowID, PolicyName.."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `opcache_get_configuration` and `opcache_get_status` methods.",
      "reference": "I really dislike this alignment approach, as it makes identifying individual functions quite hard, but I kept consistent with the previous style. Since no sorting was evident, I pushed it to the end of the block. Meanwhile, is this supposed to be tested or meaningfully testable somehow?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Could also consider modifying the ActiveExecution..."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea to use `astroid.Index` as the value of `astroid.Index`",
      "reference": "Does it make sense to change that to a custom error instead of `ValueError`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I guess this will need to change soon."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Restore this spacing - not sure why it has to be removed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "These defines cause issues in base.h leading to failing android builds. Locale independency is now set in multiple spots, in cmake and in base.h. The base.h uses feature test macros wrong. Feature test macros can be used to indicate that a feature should be made available. They do not guarantee that it is available. On the cmake side this is done by the check symbol macros (similar to what autoconf does). On the android side not. I would suggest removing this from base.h and define locale independent in gradle. It is available since android 21 I believe. Is there a way in gradle to set locale independent only if android api >= 21?"
    },
    {
      "prediction": "I think this is a bug in GoPlanner.mToNStepsPlan.",
      "reference": "Why not delete these codes?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If pull message failed after some reties, we should ensure the storaged exit, otherwise it has risk to loss data."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "looks like you don't need to import first and count here anymore"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "FYI, visibility task processing is local only, meaning pushing something to local ES cluster / local archival endpoint"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "This import can be removed."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "1. Nit: We can have a general helper to identify if a region is pseudo region. We might already have one somewhere. 2. Does any type of ARN support FIPS? If not, we may just move this check in arn package?"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "is this phrase completed in a next line? Or forgot to add... what?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "`('train', 5)` and `('train', 1)` are actually the same."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would it be too complicated to refactor `currLimit` to be an `int64`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Would it be more performant to just `include ::RSpec::Core::Pending` here? /cc @myronmarston"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should be podiochaos?"
    },
    {
      "prediction": "I'm not sure if this is a bug in the future.",
      "reference": "Is the `codecs.register(lambda name: None)` gracefully handled by codecs? The lambda is expected to return a tuple of functions (encoder, decoder, stream_reader, stream_writer) (or a CodecInfo object), according to the docs. I've only checked python's built-in help, though."
    },
    {
      "prediction": "I think this is not a valid instrument name?",
      "reference": "in this case, it could be either instrument name or the view name, which could be invalid. might be better if we can offer very specific message. (not blocking this, we can add this as a follow up,if needed)"
    },
    {
      "prediction": "I'm not sure if this is a w3c window, but it's not a w3c window.",
      "reference": "I'd rather just send the parameter twice than break encapsulation here. There's already precedence with webelement IDs"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "You may put 'open-mmlab://res2net101_v1d_26w_4s' here. MMCV will be updated later."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "May be worth making this more specific, to avoid potential conflicts, maybe `pagespeedDashboardWidget`? Or `webVitalsDashboardWidget`?"
    },
    {
      "prediction": "I'm not sure if this is a real error, but it's a real error, but it's not a real error.",
      "reference": "I guess this assignment is now redundant?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "See above note re: blockNum synchronization."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "wonder if we could avoid doing named imports if we type aliased `backoff.Backoff` in the `.../agent/common/backoff` package?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Or maybe put into alphabetical order with the other #includes."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This runs the entire duration of the program; this change is not needed."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "I don't feel well about the `ALWAYS_UPDATE` option   &nbsp; sounds like a workaround. I can imagine that some of the plugins want to observe all options. Maybe, in that case, we can reuse the `CONFIG_KEYS` that would return an empty array for observing all settings and `false` for disabling observing at all? I just thinking aloud - Like `CONFIG_KEYS` sounds reasonable. We could support and maintain it in the future, even after implementing the \"observability\" to the MetaManager then `ALWAYS_UPDATE` ... I don't know :)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "A \"tab difference\"? As in, there are tab characters somewhere? This disabling of clang-format for all the code here seems like overkill. Are you sure there's not some other solution? I don't really understand the problem though. Do you mean clang-format-diff?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Could you please leave the explicit imports?"
    },
    {
      "prediction": "I don't think this is a bug in GapicInterfaceConfig.",
      "reference": "Can we check for containsKey here?"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Exit successfully. We served the help the user wanted."
    },
    {
      "prediction": "I don't think this is the same as initialWorkingDir.",
      "reference": "Had to rename this because `InitialPackage()` already existed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we put this in a different helper?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure where your 31 comes from? I see 15 here and 2 above for pc and flags, for 17 total beyond the SIMD."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "If you want, you could change this to `allowCors(response` (like in \"version\", above) to allow Cross-Origin Resource Sharing. I'm sort of wondering what's returned if no API terms of use are set."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Why do we need to override this if all we're doing is passing it up?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Just wondering whether it's safe to send all CQDs to the child compiler. As this missing CQD is causing trouble, maybe some other user CQDs that now get sent could also cause the statement to fail? Also, if I have a table with a nullable unique column, should I have to set this CQD to create another table like it, or should the CREATE TABLE LIKE work without the CQD?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "EARLIEST_TESTED_RELEASE might be slightly more clear"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I think replacing `.*` with `\\s*` from after the hash makes sense, but not the rest of the changes."
    },
    {
      "prediction": "I think this is a hack, but it would be better to use `json:\"action,omitempty\" protobuf:\"bytes,6,opt,name=action,casttype=github.com/vmware-tanzu/antrea/pkg/apis/security/v1alpha1.RuleAction` instead of `json:\"action,omitempty\" protobuf:\"bytes,6,opt,name=action,casttype=github.com/vmware-tanz",
      "reference": "interesting .. did not know varint tag covered bool as well"
    },
    {
      "prediction": "I'm not sure why this is a bug in the future.",
      "reference": "Could you please elaborate the reason for not using `gkc_summary` like the values above? I ask this, because I assume what we want to collect is a histogram of event loop latency, and we use `gkc_summary` for collecting histograms."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "getHash should be a public and without an `_` if used here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Unrelated to these changes -- we will probably want some special handling for genesis block validation."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is probably overkill since we don't actually need to pass this specific interface anywhere, but I don't mind it!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@janos I moved this back here, to avoid having multiple add peer calls being handled. I think it's either this or a global lock across the whole function. I think this is a better approach, especially since `hive.Broadcast` is blocking . We can remove the map entry on errors if needed. LMKWYT?"
    },
    {
      "prediction": "I don't think this is a problem with the `approver_response_path` method.",
      "reference": "Minor: can we put the conditional outside of the partial?"
    },
    {
      "prediction": "I think this should be a list, not a list, but it's not a list.",
      "reference": "We need to find something more efficient than this. We can probably just check the first element and assume the type list is consistent.."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with a cron schedule.",
      "reference": "How \" via service code in response to event.\"? I don't think we'll get in the no schedule option to the release. We should probably wait for some customer feedback first to make sure we're addressing different event-triggers the best way"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please move unrelated formatting changes to their own PR (same with the resources.py file)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Make this a public attribute (remove the leading `_`) if you want to access it from the outside."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this conditional is useless now so it should be removed"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`vecofstructs->size()` already returns a `uoffset_t`. So if you just change the type of `i`, you don't need any casts."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: Maybe merge this with the configProto check on line 208? Don't feel that strongly though, please keep separate if you prefer."
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case.",
      "reference": "I know we already did this in 4.0 so carry on, but I'm facepalming here we should've made an overrided setMessageHandler that sets ismaster to true when hello is present. Esp in 4.0 where we already have some overrides written. We can keep going here and maybe open a ticket to some effect of that solution"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `data-turbolinks` attribute.",
      "reference": "I believe we could use `link_to` here (although not super important). Also, we should internationalize this value. I'm not 100% sure what our process is for adding new UI strings these days (e.g. skip the specs that will fail if we add a new key to only one language, use Google Translate to translate the value for us, some other option)."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "This was already in vkGetPhysicalDeviceDisplayProperties2KHR..."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "nit: I'd expect a public method called IsDockerEngineRunning to return a boolean yes/no, not the error message. Can we change either the return value or the name? Something like `CallDockerEngine`"
    },
    {
      "prediction": "I don't think this is the primary key, but it's not the primary key.",
      "reference": "If i remembered correctly, type_name is '{RESOURCE_TYPE}/{RESOURCE_NAME}', if type_name is 700 max then name cannot exceed that size"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "When calling functions with keyword arguments: please provide the arguments as keyword arguments, not positional arguments."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "We may follow the argument order: conv_cfg, norm_cfg, act_cfg."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `options`?",
      "reference": "`options['binary'] = WebDriver::Chrome.path` if set?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "folly library should be put on the top."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we have to restrict this to SVG elements? I think setting namespaced attributes on normal dom elements (while not as common) is still valid, so perhaps we can save some bytes by removing the `isSvg` check?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Please add it to the `REMOVED_HOOKS` constant."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This variable needs `.v1` at the end of it, or the tests below need it. There are some test failures as a result"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `id` parameter.",
      "reference": "Is this access protected so that only admins can access this route?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "What happens if the minimum x coord is > 0? This will incorrectly set it as zero, right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think you want to look at current pending + batchSize and if that is > o.maxp no?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Should this be `codes.Error`? `codes.Internal` was an error status before."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `page_header` parameter.",
      "reference": "I don't think you need these lines."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "You didn't mean to export this, right?"
    },
    {
      "prediction": "I don't know how to do this with the `sns-ruby-example-show-topics.rb`?",
      "reference": "Simple Notification **Service** (singular)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we still need this?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We do have a disconnect between the privateMarkerTransactionFactory.getSender() call and the createPrivateMarkerTransaction() call. When the plugin receives the call to create the PMT it does not know what the sender was returned by the other call. At a minimum we need to pass in the sender to the second call. I would prefer that the plugin does the locking if that is necessary. If you are using random keys you don't have to lock! Besu could signal to the plugin when a PMT was un- or successfully added to the pool using a callback. Callback could be null if this is not needed. The plugin would have to be able to get the nonce for a certain key from besu. What do you think?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This is a bit inconsistent with the `ErrorStartHourGreaterThanEnd` in the previous file. Wouldn't `ErrorDefault``fit better here?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think it will revert the change @antoninbas did on purpose 05eee251c9c53400277def576f92d614ca234898"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "nit: a switch perhaps?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Would it make sense for `opensearch_description_tag` to have default values for the title and href attributes?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Just noticed this while debugging -- it's unlikely to be causing issues in practice."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "That seems unrelated - did that fix a random test failure you noticed while working on this issue?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This kind of concern should be handled in the `TableMetadata` update methods. This is similar to `metadata.rollbackTo`, which not only sets the current version, but also updates the table history. I think that all of those methods should add the current object's `file.location()` to the previous metadata location list, if it is non-null. That way, the caller never needs to remember to update it."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "We need to know why all the tensors are detached in `get_bboxed`."
    },
    {
      "prediction": "I'm not sure if this is a class method, but I'm not sure if this is a class method.",
      "reference": "Unrelated but shouldn't this raise `attribute-defined-outside-init`?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I would rather no have this as a `kwarg` as it encourages \"growth\" which lead to an unweildy constructor in other classes. Let's add a method or property to take care of this instead as I think it's usage is going to be quite low."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You just changed my life :) I grew very attached to this safe nav approach when working with Groovy years ago `obj?.method`. Glad to see its now a part of Ruby!"
    },
    {
      "prediction": "I don't think this is the right thing to do with the form-group clear-fix.",
      "reference": "do you mean 'clearfix' class?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `options.causalConsistency=true` or `options.causalConsistency=false`.",
      "reference": "`causalConsistency` is already defined on `SessionOptions`. We do not need to duplicate it here."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `assertj.core.api.AssertionsForInterfaceTypes.assertThat` method.",
      "reference": "This should not be included since there are no code changes."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "If all we need just response 200, then we could use `c.Status(http.StatusOK)` here."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Should be checking for error here"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Put a space between `(array)` and `$this` and I'll merge it"
    },
    {
      "prediction": "I think this is a stub.",
      "reference": "You could add this to stack.go, which has similar functions (to avoid yet another small file). None of these are likely to be implemented considering what TinyGo is designed for."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "the class names `NotificationHolder` and `NotificationsHolder` are fairly difficult to quickly tell apart, particularly since they are often used close to each other"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Avoid wildcard imports"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Need to do this to unblock mockgen. The interface method needs to be public to be visible in another package. The right fix is to delete this test only interface method"
    },
    {
      "prediction": "I don't think this is the case for `loadbalanced` and `loadbalanced`",
      "reference": "same question here as I have on the other file regarding doing this check here vs L112 vs not at all"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "Adding `// +build !windows` (as a separate line) will do the same for Windows. So while you are at it we might add it as well."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `requests.Session` and `requests.Request`",
      "reference": "this is used as important way of mocking for unit tests, FYI"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `muted_alpha=0.2` option.",
      "reference": "Sorry, should have been clearer, I meant adding this to the ``Histogram`` options one line above."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just ignorance on my part, but what is the significance of the change from C23NHe2 to C23NHx2?"
    },
    {
      "prediction": "I think this should be a list, not a list.",
      "reference": "What about tuples or pandas series? Do we want to support lots of different types or force a single type?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Small thing, without the check above this will throw a NoNodeException if the path doesn't exist. Maybe this can be wrapped in a try/catch just for the NoNodeException, so that the more user-friendly message used above can be thrown instead: `throw new KeeperException.NoNodeException(\"No collection found at path: \" + path);` Just a thought, I'm not even sure it's worth it."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I don't know why this worked before, but we should be explicit on not verifying that a blank string (allowed as a way to remove a url/download_url) is a valid url as it is not."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do we want to raise an error here instead of warning? Or would it be better to just see if Bolt happens to succeed, and let it fail on it's own if it fails? I'd lean towards raising an error, but that's different from \"removing support\"."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the transport class.",
      "reference": "This is kind of confusing with the other `filter_options`."
    },
    {
      "prediction": "I don't think this is the case for the `deleteFromFavorites` call.",
      "reference": "Could the `deleteFromFavorites` happen when `head == nil` because it's not initialized yet somehow but not because TLF doesn't exist? I was concerned if this would make it possible in any way to have favorites seemingly deleted on a device while it's not actually happened on server."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It doesn't look like this particular \"rowCount\" variable is used anywhere. I suppose we could delete it. The code change is harmless though."
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "Hmm, probably we should instead write whatever `status` is returned instead of coding a special case."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Could using the pointer-to-struct approach here cause confusion later? We've had several problems of that kind in the past. What does it mean if the struct is non-nil but its fields are nil? Is that even allowed? (libcalico-go question) Are there any validation requirements for this new rule addition; should it only be allowed if `Protocol == TCP`, for example?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why this recursive relationship definition?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "More sentence, less list please. > Encoding of the handler. This field is optional. We don't need to mention exactly what it's used for because that list can expand (as it has already in this change)."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Not part of this PR, but should the section above say what the name of the metric is for each method?"
    },
    {
      "prediction": "I think this is a bug in OpenTelemetry.",
      "reference": "there are changes that are upcoming to this section. For now, this works (to demo the usage of Gauge), and the changes to this section are coming as separate PRs."
    },
    {
      "prediction": "I don't think this is the case for the background process?",
      "reference": "This is equivalent to stdout. Why not just replace stdin with stdout in `IsProcessBackground`?"
    },
    {
      "prediction": "I don't think this is a `nullptr` here, but it's a `nullptr` here.",
      "reference": "Rather than test for nullptr, just treat the pointer as a bool, i.e. `if(p_jmsg[\"compress_method\"])`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the container manager?",
      "reference": "Can we move the remaining code of this method to a new method? I don't like the `return;` here, we could try to replace it with an `if ... else ...` syntax. What do you think?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "nitpick: _and collections_"
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the case.",
      "reference": "I believe these need to be explicitly initialized in `proxy_send_prepare`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is unnecessary. The declaration of `t0` on line 179 is still in scope inside the `except` block."
    },
    {
      "prediction": "I think this is not a good idea.",
      "reference": "The `border_color_`... properties don't support solid colors, not only this one. Maybe `@param solid_color` should be used instead of adding this note to every one of them?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We don't need this file, we can use the one that is in the grid-ui directory"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "FYI: inlined this method in the internal review."
    },
    {
      "prediction": "I'm not sure if this is a bug in the code, but it's a bug in the code.",
      "reference": "Werid, the checksum between this file and the one on branch `develop` is the same not sure why it's showing a diff"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Prometheus doesn't have concept of Meter (like OTLP does).. Trying to see if this is a good approach to use the meter name as namespace, to avoid name collisions, when same instrument name is used across multiple instruments, from different Meter."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "The formatting of this is a bit strange; I'd suggest collapsing this back to a single line, and moving the `&&` to the beginning of the second line to meet the line length restriction."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "One or the other should be non-NULL. If segments is NULL, the alloc above will have size zero, which we do not allow (there's no header): it should assert in debug build. So there should be asserts that one is non-NULL at the top, and if there really needs to be some kind of defensive check down here, it should cover the alloc too."
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `email_address` attribute?",
      "reference": "I'm surprised rubocop isn't picking up singe quotes?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is this line still needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe use specific values for all the watt.times fields? Even better, have a const for it at the top of the file?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "nit: UNICODE_BRAILLE_TABLE or something might be a better name for this. IMO, braille-patterns.cti is a terrible name. This table allows Unicode braille characters to be used anywhere to produce raw dots."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why are we removing the option to skip machine pool generation?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "\"Request line\" here too."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Please remove this."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Weird bug. Combining those joins and group calls was triggering AREL to generate the sql cache inside of will_paginate before the final call. This is a harmless workaround, but hints that will_paginate might becoming seriously deprecated."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This can be simplified as discussed before."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Does `internal` or `test` in the file name actually do anything here? Or is that just to show these functions are only for tests?"
    },
    {
      "prediction": "I don't think this should be the case.",
      "reference": "does this boolean indicate unsafe serialization?"
    },
    {
      "prediction": "I'm not sure if this method is implemented.",
      "reference": "Maybe rewrite to `Is only implemented for React Native`? (I assume that is the case)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we not need this in Java because Java *is* handling map responses?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Maybe \"For configuring which scheduler messages can be received.\"?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "It will stop working with orm, so this is not a good fix, Try using some method in a common interface"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "`s` is not necessarily the same as `sampler` - sampler could be null and this crazy lambda underneath falls back to something. So please use `s`"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This code is a bit confusing. Should HttpParameterType set to the original one or it is always BODY?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why did this change?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: `status` collides with imported package named `status`"
    },
    {
      "prediction": "I think this should be a function that returns true when the catchpoint file is being generated. I think this is a function that returns true when the catchpoint file is being generated.",
      "reference": "\"memory pressure could be decreased\" --> \"to avoid memory pressure\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think it would make sense to fetch the cache values after deleting the listens and making sure they are what we expect."
    },
    {
      "prediction": "I'm not sure if this.headerStateManager.mapStateWith(collapsibleColumns) is the same as this.headerStateManager.mergeStateWith(collapsibleColumns);",
      "reference": "I'm thinking about covering this change with the test. Can you do that?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure if it's a good idea to remove stop channel. If user cancels connection how will you stop pinger?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could you please add a `TODO` here that we won't need `docker.AuthConfiguration` anymore when we migrate to SDK's pull image?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `BlobNamePrefix` and `BlobNames` properties.",
      "reference": "Is there a scenario were we want to get an arbitrary set of blobs that don't share a common root?"
    },
    {
      "prediction": "I think this should be a test suite, but it's not a test suite.",
      "reference": "Can you leave a note about why we are skipping regex tests?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "This was the only caller of CreateRepo, so I inlined it."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "As this is already a child of `auth`, I think we can shorten this to `path`"
    },
    {
      "prediction": "I think this is a bug in the UIA text pattern.",
      "reference": "This call should use element, not 0 I think."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `options` argument.",
      "reference": "This is missing the definition of `fetch_until_empty_page` - it needs to go in the config section above."
    },
    {
      "prediction": "I don't think this is a bug in Selenium.",
      "reference": "I don't think this one needs to be changed since the only previous path is already an absolute one."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since we kept the original constructor we might not need this change now."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There is already a log in `BaseMetastoreTableOperations` for this. It has the location, but not the table name. Maybe just add table name to that one."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This should be in the last group."
    },
    {
      "prediction": "I think this is a bug in Datadog.Trace.Agent.",
      "reference": "I believe you should either remove this or rename the PR. You can't change the behavior of the tracer (even to fix a bug) in a PR named \"unit test improvements\""
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I've gone with this group name, however I'm open to suggestions on alternatives!"
    },
    {
      "prediction": "I think this is a hack, but I think it's a bug in the future.",
      "reference": "should this be GOQUORUM"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think checkCoinbase is not skipping checking coinbase. Instead, true-> checking num(coinbase tx) = 1, false -> checking num(coinbase tx) = 0."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "same here, move it out"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can you elaborate on why you need different behavior depending on Tools being built independently or not?"
    },
    {
      "prediction": "I don't think this is the case for example answer and guidance.",
      "reference": "because of the above if statement will requires both ex_save and guid_save to be true, this code will always return 'example answer'. This should be revised with `example_answer.present?` and `guidance.present?`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "why not context from stdlib?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just saw this and wasn't able to hold myself from renaming :-)."
    },
    {
      "prediction": "I think this should be removed.",
      "reference": "Can we keep the other assertion too? I think it's helpful to ensure that the uninstall function was called too"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`warn_with` prefixes the message with `WARNING:`, right? So this will put `WARNING:` twice. It would be good to verify all the warnings look good after this change, given how easy it is to make a simple mistake like this :(."
    },
    {
      "prediction": "I don't think this is a bug in the go-filecoin project.",
      "reference": "FYI In the message queue I use the term \"stamp\" to refer to the time-like mark associated with each message. It's opaque to the queue/pool and should make no difference if the stamps and age limit were converted to seconds. So this could then become `Stamper` with `CurrentStamp()` method, no reference to \"blocks\" or height etc. The wrapper struct could be `StampedMessage. The interpretation as block height is deferred to the user/constructor that hooks things up, the \"business logic\". This is just an observation, take or ignore as you wish."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we remove the `TODO` statement here? (as this is actually fixed in this PR)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "m prefix no longer in code style"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "need to filter the entities in buffer as well"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please add spaces before and after the equals sign"
    },
    {
      "prediction": "I don't know how to include this file?",
      "reference": "This file could also be cleaned up/deleted. But lets do this separately after ensuring all the event logging has been ported to the current logmxevent_traf.cpp file completely."
    },
    {
      "prediction": "I think this is a bug in RSpec.",
      "reference": ":thinking:, the line number here is the line of the example (`example.location`), that's probably why I finally chose to display the example title because it's what can be found on this line, and saying that the error is from there is confusing. But presenting the actual failures is indeed better, so maybe we can get the failure actual line number from the exception backtrace and then output two distinct lines for failures like this one?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `keep_alive=True` argument.",
      "reference": "We shouldn't add this as a new `kwarg` here. This should all be done on the options class"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should this be `OS_VOLUME_SUPPORT` to match the symbol key names?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "In C, file scope variables are already initialized to 0 so the \"= NULL\" is redundant. Not a big deal."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "on line 40, the `relevantNode` can change and therefore the `doc` might change too for the lookup on line 43. I think this code should be moved to where the `doc` is actually being used"
    },
    {
      "prediction": "I'm not sure why this is a bug?",
      "reference": "nit: just to be similar to others, can you change to interpolation?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Would this make more sense as an option on an Issuer resource (specifically on the CA issuer) rather than as a flag? It's not ideal that we have a flag that _looks_ like it could be 'global' but is actually not IMO. Also, if Istio is reading the CSR object, is it possible for it to read the CA from the CSR itself too and append the two instead? Not sure if we ever decided whether to use annotations for this purpose @JoshVanL?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Because this acts as a coordination point between client and server, it should go in core.py instead of const.py (so eventually the server could use it to guarantee that it delivers dates in the expected format)."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "expected statement, found 'else' (and 1 more errors)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "IMO this doesn't need to be in the `kbfs` repo. And I don't like setting the byte. We can always compare with the randomly generated `TlfID`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "What's the difference from ModuleName in `pkg/apis/meta/v1alpha1/types.go`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the newtonsoft.Json.Linq, but I'm not sure if this is the right thing to do with the newtonsoft.Json.Linq, but I'm not sure if this is the right thing to do with the newtonsoft.Json.Linq, but I'm not sure if this is the right thing to do with the newtonsoft.Json.Linq.",
      "reference": "We shouldn't be changing this task as we are trying to break our dependency on it and switch to using the shipped version."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Shouldn't we have a low bar for generating out-of-line context switch, i.e., if we need save more than n (3?) simd or m (4) gprs we should go out-of-line? And it should be || instead &&. It seems the bar is still very high after this change."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "Should the API have a dependency on the SDK?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Is this a sometimes leaky test?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It should be possible to create a test case that enter the loop. That would be a good enough test case for me. Have a look at the extern type inference test cases that already exist. Since you can just pick the type variables the extern type use, you should be able to create a conflict that requires this loop to fix."
    },
    {
      "prediction": "I don't know the language.",
      "reference": "It might make sense to log this."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Line is too long. [84/80]"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nice touch since Google likes to change things every now and then."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Thank you this is so much nicer than the old `Rails.configuration.branding['blah']['blah']['blah']` :)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: Would you mind alpha-sorting this?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "For my understanding, the DATA manifest & DELETE manifest could share the same read / write path so I think we could use the common reader+writer. Is there any other reason that we need to make them separate paths ?"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `contact_us_url`?",
      "reference": "that change should be sufficient for avoiding the override of contact_us_url helper. The one defined at the .yml it is within a hash so no problem should arise."
    },
    {
      "prediction": "How to do this?",
      "reference": "We actually had a discussion about this exactly in #3470, some languages seem to go for one, some for the other  "
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Is PHP the first dynamic MVVM language with grpc streaming support?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "the `if` isn't necessary here; it's safe to call `delete` on `nullptr`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Change if the method's name finally changes to `clear_history` as proposed elsewhere"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "can this one also be moved to the top of the file?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "So if I understand this correctly the externalEntities should be computed and stored in GroupMember, while current code usage of GroupMemberPod will be migrated to GroupMember later?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Don't we have tests to change after this breaking change? probably we're not using hard coded strings in our tests when we create a `Span`?"
    },
    {
      "prediction": "I don't know how to use `os.environ['GOOGLE_APPLICATION_CREDENTIALS']`?",
      "reference": "will this fail if the env variable doesn't exist? Is this the preferred behaviour?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "bad line wrap"
    },
    {
      "prediction": "I don't think this_l should be used here.",
      "reference": "What does the `8` here represent? Can you give it a name?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "`MPRester(os.environ[\"MP_API_KEY\"])` can be left simply as `MPRester()` and it will pick up the API key from the environment. What is the purpose of this file otherwise? Is it better suited for `dev_scripts`, or a test?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Looks like there may be more changes to this file than intended?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "when message type is not expected, contine to next loop instead of return to finish infinite loop"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This change was not really intended but made by the linter of VS Code. And looking at other packages this looks like a best practise to place interal packages on the top and gh imports afterwards."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "instanceID should stay the same for a AWSMachine?"
    },
    {
      "prediction": "I don't think we want to use the `s3Proxy` option.",
      "reference": "Since this is a dict don't you want `False` or do we clean that up elsewhere?"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "what's the reason you had to add the `host` argument to all `get_work` calls?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure how to do this?",
      "reference": "This will never be a dataset so we can simplify the code here"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "This should be moved into the PrivacyBlockProcessor instead of adding the constructor here."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "nit: Remove \"insightfilestore\". I think \"insightstore\" is good enough and as I see we are using that name at other places too."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "It looks like you've removed `bisect_round_finished` but kept `bisect_round_started`. Seems a little odd that they aren't paired. Not sure if there's anything to do about that though..."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I'm not sure how to fix the lint and mypy warnings on this line. I could just ignore them, but I feel like the linter should know this exists."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "why remove `Symbol`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why are currency signs considered punctuation? They technically fall under the BMP range for Currency Symbols `\\u20A0-\\u20CF` (covered in `getUnicodeNonBmpRegExp`, which is itself a misnomer)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "You have forgotten a coma `,`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For different datasets, we may want to save the images differently. Sometimes the datasets are categorized into several subfolders, and we want to keep it when saving visualization results, and sometimes we just want to save all images in `out_dir`. An argument may be added to control the behavior."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "if `other` could have a guaranteed `0` byte in it, this whole `if` could be removed, and above you could just add `|| c2 == '\\0'` to get the same effect?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "nit: can this be a primitive value?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "This maybe not what we want. If `rewrite` occurred before, `r.URL.Path` contains the result and we should use it. Otherwise `rewrite` middleware will disfunction when combining with `browser`."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Why change this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "  _nitpick_ Isn't it now actually NotLogFakeHttpExceptions**Error**Listener ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not just look for the \"type\" property instead of creating a ResourceType property?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should use `bc.config.Blockchain.ChainID`"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "this doesn't need to know about NativeClient"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I know we discussed if we should add in the resource_name to the hash, and I actually don't think it's required. The violation hash was recently updated (not released) to include the violated rule, so when the next release goes out, user's findings will get updated. The resource name doesn't hurt to have here, but not required."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "The variable name is also misleading imo. The width from the buffer comes from `wl_shm_buffer_get_width` (or a similar EGL thing), which is what gets encoded into `surface->texture->width`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `recording_msid` field.",
      "reference": "Why are you using these tags to carry these msids?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "flb_strdup() should do the work here. note: use Fluent Bit memory wrappers"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This line should be separated from the package declaration by one line as it is not the package description."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "shadow: declaration of \"err\" shadows declaration at line 410 (from `govet`)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `duration` and `until` parameters.",
      "reference": "Maybe next time better to make separate PR?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "line 316 also handles this case, need to simplify the logic."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "We used to have a simple check for bucket and object names, we then decided to remove it and rely on the backend service to check for the name. Is there any reason to add an empty name check now?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Line too long"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This isn't aligned though."
    },
    {
      "prediction": "I don't think this is the case for the test-time augmentation.",
      "reference": "it is mean -> it means PAAHead does not support test-time augmentation."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "@lnielsen-cern thanks. I missed it :("
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `analytics.pagePath:${ href }` instead of `analytics.pagePath:${ href }` instead of `analytics.pagePath:${ href }` instead of `analytics.pagePath:${ href }` instead of `analytics.pagePath:${ href }` instead of `analytics.pagePath:${ href }`",
      "reference": "@tofumatt, has it been changed intentionally? It doesn't seem to be required in IB, plus we haven't had `content-drilldown` before... If it has been changed intentionally, then should we update the `AnalyticsDashboardWidget` component to be use `content-drilldown` instead of `content-pages` as well?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "nit: don't think an extra line is needed here; as retrying is an installed library and should be grouped with the rest of the installed library."
    },
    {
      "prediction": "I think this should be done with a proxy.",
      "reference": "This should be a bool"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`if (llvm::dyn_cast_or_null<swift::WeakStorageType>(GetSwiftType(compiler_type).getPointer())` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The `generateVariantWorkloadManifests` function below relies on the config manifests specified in Git, but it was passed with the newly created canary's manifests where their name was updated."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "are this docs neccesary ?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "Can you please revert changes to files in the `thoughtworks` package? This is legacy code and we will eventually phase out RC."
    },
    {
      "prediction": "This is a hack.",
      "reference": "This change suppose to resolve issue #2968. `loss_weight` should be of length 2, the second entry is ignored."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is there an easy way to check for conflict suffix to avoid false positives here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `apply_prep.get_task` and `validate_prep.get_task`?",
      "reference": "`apply_prep.run_task` also seems like it can just use `@context.run_task`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "do you have any idea on how to fix it?"
    },
    {
      "prediction": "This is a hack to make sure we don't close the file after the test is closed.",
      "reference": "You don't need to fix this (you've done so many iterations). But for next time, you can make this into a docstring so it'll have a nicer descriptive name when the tests are running."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "When does 'expiresAt' change? Do you need this?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "There are enums for genders + `PLAYERSEX_LAST`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should this use the constants as well? Or intentionally covering the fact that the constants may change"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `__getitem__` and `__getitem__` and `__getitem__(self, which):`",
      "reference": "The case of a negative size (= keep all elements) was not handled in this function."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think we should keep this dynamic config knob for operations purpose."
    },
    {
      "prediction": "I think this should be a test case, but it's not a test case, but it's not a test case.",
      "reference": "Was this intentional? Perhaps this could be replaced with another way to check the offsets?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "the buckets are created via the stackset, customers don't need to provide them"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This doesn't have the same behavior as before. Maybe you want `reverse_merge` (and it either just works or we implement it on `Blacklight::Solr::Request`)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `cabal update` command?",
      "reference": "This should be ` /$(ghc_find #{config[:ghc]})/ ` instead of ` /#{ghc_version}/ `, I think."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We should deprecate this at some point."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Move these two arguments before `loss_cls`."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "[Super NIT]: i := serialNumber if i == 0 { i = mathrand.Int63n(...) }"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the tool format.",
      "reference": "-f short form here collided with --force. :)"
    },
    {
      "prediction": "I don't think it's a function, but it's not a function, but it's not a function.",
      "reference": "I think it is better to describe in the release note that `rerender()` was removed."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "We could also test this easily with `runpy.run_module`, what do you think?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is it OK to fall through if it's not assignable? I was kind of surprised when the tests passed. Maybe one of the options below ends up working? For the new tests, this panics because `**not assignable uuid.UUID to []uint8**`. `uuid.UUID` is an array, not a slice."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "I know this is after the fact but imo blockAPI should be blockMiningAPI."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "it's just a pattern as it was. SystemAttributeCode should have it's own definition and validate by it"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Similar to the code block when we use prefix, maybe we can unify them to base?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "I think `Duration` is useful for this action and we shouldn't ignore it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Everything below here can be replaced with `return s.err, len(p) - len(s.dataForWriting)`."
    },
    {
      "prediction": "I don't think we need to do this here, but I don't think it's a good idea to use `desul::Impl::init_lock_arrays()` instead of `desul::Impl::init_lock_arrays()`?",
      "reference": "Again, we can also guard `g_host_hip_lock_arrays.atomic`, can't we?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Variable name should start from lowercase latter"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why has this timeout doubled?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should IptablesPostWriteCheckIntervalSecs be set back to its previous smaller value, if use of the iptables lock is disabled?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You're missing a `return` here, but I'll add it :smile:"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Can you try adding back this assertion? I'd like to assert that the texture has been created in the same context as the renderer."
    },
    {
      "prediction": "I don't think this is the right thing to do with the plural endpoint.",
      "reference": "This won't work with Python 3 because it will already be a string. In that case we need to use `decode_header` from utils."
    },
    {
      "prediction": "I don't think this is a bug in Mongoid, but it's a bug in Mongoid.",
      "reference": "Why is the respond_to check here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@orklah are you sure it's the same as `$chars[$i]`? It looks like `$i` is changed above, after `$char` assignment."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I have a question? How do I construct a indexManager for testcase?"
    },
    {
      "prediction": "I don't think this is a bug in the library.",
      "reference": "These checks aren't needed. See pluginmgr.c : opae_plugin_mgr_load_dflt_plugins( )."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please take a care about prefixing."
    },
    {
      "prediction": "I don't think this is the case where the account does not exist. I don't think this is the case where the account does not exist.",
      "reference": "this line doesn't match what the rest says"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Since it's not working for linux, maybe leave the !linux in there as well?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we remove the key-value pair entirely? Same for workflows in general. We have a \"sourceExists\" method that checks if a key is there if I remember correctly."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Unrelated bug fix"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "We probably want to let the translation library handle the string replacement for these as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should combine these 2 list (list_gossip and list_db) into just one list command, and show the discrepancy between the 2 if any."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `approve_reject?` method. I'm not sure if this is the right thing to do with the `approve_reject?` method.",
      "reference": "What do you think about prefixing the Policy method names with `can_`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Based on the docs, credential process can return a key `SessionToken`"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `moment(birthDate, 'LLL').toDate()` and `moment(birthDate, 'LLL').toDate()` instead of `moment(birthDate, 'LLL').toDate()` and `moment(birthDate, 'LLL').toDate()` instead of `moment(birthDate, 'LLL').toDate()` and `moment(birthDate, 'LLL').to",
      "reference": "I think this if should be removed (see issue)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I would avoid importing `felix/ipsets` package because this package is the windows equivalent and should be at the same level of `felix/ipsets`. We could add linux specific dependencies into `felix/ipsets` later and it will break Windows build."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nitpick: Please move this down to the other imports, as it's a Python stdlib import."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "\"for getting started guides\" reads a bit weird, like it's missing punctuation. Maybe just \"for a tutorial\"?"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "This looks like a dead parameter -- maybe a copy and paste error. If it's truly unused, maybe you can open a separate PR to simply delete it, and then it's one less detail to worry about here."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Nit: Should we add support for `int` and `uint` in the `values.New()` function? That would allow us to to handle all of these types in one case. Maybe there's a good reason why we don't do that already, but I'm not sure what it is."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "if you are not dealing with cache now, please revert these changes. On their own they make little sense"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Wearing my extra-douche-bag hat I would say not spaces on a blank line. Maybe at some point we could have some automated process remove these things. For now I would not bother changing it."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "I think it would be better to use an `ItemUpdatedEvent` like for the \"prefer streaming\" preference. We already have a ton of events that need to be handled in all list fragments that just do the same everywhere. I think we could even remove some of the existing events in the future."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `slug` column.",
      "reference": "I think we have to manually write a down for this migration."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think we still need this check, but I'd leave it as an assertion for now."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `updated_at.to_i` or `updated_at.to_i`?",
      "reference": "Since this may be the case, wondering if we should call the param `updated_at_i` or something so that we don't run into a problem distinguishing them down the road?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "wondering why we need to join the paths here; seems evt.commandLine only takes whatever appExe is"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "1.not format code 2.failed but still continue? 3.\"UTF-8\" can changed to java.nio.charset.StandardCharsets.UTF_8.name()"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I'm wondering if we should add this to a `utils` module in `astroid`. Porting the util to `pylint` doesn't make sense as we would need to duplicate the globals that are being used in the function, but importing from `brain` also feels weird. @Pierre-Sassoulas Do you have an opinion?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This seems different than what we do for corrupted request headers. I would like to determine the correct behavior and consolidate this logic."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Please make the change in the CAI inventory, rather than changing the scanner."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "adding this `abstract` is a breaking API change. Even though I agree it makes perfect sense to have it, we can't break this API until PMD 7.0.0. We should revert this particular change. We could make a reminder ticket like we did with #463 for 6.0.0"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is following the existing convention, but I'm not sure the convention is a good one. I think it would be better to have one shared example group: - It means we don't need to add new example groups twice every time. - If the shared example group looks large, that makes it more obvious that our team models have too much shared behavior. I don't want to do anything about this right now (I'm pretty sure I can wipe out this shared example group when I change team plans), but it's good to keep in mind."
    },
    {
      "prediction": "I don't think this is the case where we don't know the address is IPv4 or IPv6, but we don't know the address is IPv4 or IPv6.",
      "reference": "I do not think we need to do a source code change to handle this. We could set the subnetwork to default to /32 (/128 for ipv6 ipv4-mapped)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "It looks good overall! The only issue I have is that the description string is now duplicated twice right? Once in the struct and once in the parameter string? Maybe let's pass the struct to the command so that `ostree_option_context_parse` can set it as the summary? Similar to what we do in rpm-ostree."
    },
    {
      "prediction": "I don't think this is a bug in ChromeDriverCommandExecutor.",
      "reference": "This states very clearly that this is a derivative of Chrome and not Chromium. Do we need to extract an abstract `ChromiumCommandExecutor` and have both Edge and Chrome derive from that?"
    },
    {
      "prediction": "I don't think it is a custom enum class, but it is not a custom enum class.",
      "reference": "it seems to me, the issue lies on `isEnum()` itself, returning false for something that is an enum. I'd rather change it there than here."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Please use `{}` instead of `dict()`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `useCallback` and `useEffect`.",
      "reference": "I have concerns about using this in more places before #3278 - I'll take a look at that again shortly."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "new field needs to be asserted"
    },
    {
      "prediction": "I'm not sure why this should be done here?",
      "reference": "when send log failed, why update the last sent log id?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "what was the problem with the previous order? `prepend` comes conceptually before `append`, i.e. `insert before` should be before `insert after`, I think"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Why is this necessary? Could you provide some context?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Is there a recommended quote style for attributes? I see single and double here, double further down."
    },
    {
      "prediction": "I don't think this should be done here.",
      "reference": "Please use an atomic bool."
    },
    {
      "prediction": "I don't think this is a static class, but it's not a static class.",
      "reference": "Consider naming this class `SpanExtensions` to follow C# conventions."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "FYI @lucaspimentel and @colin-higgins since you have already approved, I wanted to point out this required change. By fixing `FrameworkDescription` to use the correct logger, it created a cycle between these two static constructors, so I'm removing this log line and delaying it to when it's actually constructed later in the Tracer. Let me know if you find that acceptable or have any suggestions."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Ah, so we are going to need to update node/host files for this to work?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "This code is new and not tested well. While we may drop the log level before we ship 4.0, right now this is extremely helpful to users."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `current_user` and `current_user` parameters.",
      "reference": "used named path (`proposals_path`) instead?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `item_view.is_suppressed = false` statement.",
      "reference": "Am I misreading something, or is there a mismatched parenthesis here? Please let me know whether or not this is cause for concern -- just wanted to be totally sure before merging, since I can't test this from here. Thanks!"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Might we want a hook to allow emitting metrics or logs in the case of a permitted empty service header response (or similar UpdateSpanWithErr on empty service header in response if strict enforcement is desired by the caller)?"
    },
    {
      "prediction": "I don't think this is the default value for the `protocol` parameter.",
      "reference": "if using dict.get, this could just be `kwargs.get('protocol', 'https')`"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Add docs to the new methods here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "what does it mean enabled?"
    },
    {
      "prediction": "I don't think we need to reEncrypt all files.",
      "reference": "Getting an error when calling with db.execSQL (in sqlcipher 4.3.0, pragma returns ok)."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Maybe we could remove `\" \" + ctx.Tr(\"dashboard\")` completely?"
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "Simple Storage **Service**"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Let's add some assertions here to ensure we don't panic. Length of results. Conditionally cast second result to error."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Where did we take this default from?"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea to use `options.compareStartDate` and `options.compareEndDate` as well as `options.multiDateRange` and `options.multiDateRanges` as `options.multiDateRanges`.",
      "reference": "Let's move these down to be after all required arguments rather than in between."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we just null the Map and let the GC handle the memory? Clearing just removes items, but not capacity, so this would leave some memory on the table."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "did you mean to delete this line?"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Should we use logger instead?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I think it would be preferred to do `expect(helper).to be_analytics`"
    },
    {
      "prediction": "I think this should be a list, not a list.",
      "reference": "Actually, I think it's okay to just change to `if isinstance(key, (str)) or is_list_like(key):` and `key = list(key) if is_list_like(key) else key` for simplicity for now."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If there any other tests, I would make it optional there also."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "This can be removed too, right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If you're going to allow people to specify multiple SMTP servers, you should also properly export/import them."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "nit: Can we prefix these variables with `AspNetCore`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can this also include a quick test for transpiling by name?"
    },
    {
      "prediction": "I don't think this is a problem with the `SessionStats` type.",
      "reference": "This TODO can be removed"
    },
    {
      "prediction": "I think this is a bug in MvvmCross.iOS.Support.Presenters.UIKit.",
      "reference": "can we make tabAccessibilityIdentifier = null as default?"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "Should we print this error?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For which reason do we need to convert this to int here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "FWIW, wondering if the error is interesting here (I actually arrived at this code initially to change `supportsFreezer()` to return a `bool`"
    },
    {
      "prediction": "I'm not sure if this is a test plan. I'm not sure if this is a test plan. I'm not sure if this is a test plan. I'm not sure if this is a test plan. I'm not sure if this is a test plan. I'm not sure if this is a test plan.",
      "reference": "Does this still need to be a partial? is the intention down the line to move back towards a conditionally different title?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "seems like `RegistryURL` is missing? Same for a few other places that create `archer.Environment` below."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Are these imports needed?"
    },
    {
      "prediction": "I don't think this is a bug in IE11.",
      "reference": "I think you can remove the `(isIE11 ? it.skip : it)(` above, if you're going to skip the test this way."
    },
    {
      "prediction": "This is a hack, but it's not a good idea.",
      "reference": "IMO we should instead fix the above call to do `long actualChecksumIn = Long.reverseBytes(in.readLong());` to get the actual checksum value? This way the below error message would also be correct?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we also need something similar for `rebuild-index`?"
    },
    {
      "prediction": "I don't think this is the default configurables.",
      "reference": "I think convention is snake case for import naming?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "i think haspk is false?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "you should add this to the cover command too (but let's have a more general convo about whether it's a flag or config option)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "instead of passing in pointer to empty struct, we should make it optional and support passing nil and use default cfg if it is nil."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with pd.Series or pd.DataFrame.",
      "reference": "A fair bit faster, although still not great, hence also adding a hashkey."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the current user?",
      "reference": "If we're going to leave this in here, how about we at least pull it into partial?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This `context` is used correctly, there is nothing left TO DO."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "If `docs` is an empty array there will be an error"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is it really necessary to have the user specify this, or can the reverse proxy infer QUIC from the upstream's Alt-Svc headers?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "just remove the entire variable."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe we should put that in the option description?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `Optional<String>`.",
      "reference": "Why do we need to make this optional? Isn't the idea of the builder that if you don't need this value you just don't call the `keyFilePath ` method?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shall we do the same for ORC and Avro?"
    },
    {
      "prediction": "This file should not be used in the project root.",
      "reference": "Should be a space between line"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "if not behind interface then equally we can use SecureRandom.GetBytes directly, otherwise let us push it behind ISecureRandom so we can test with this class wherever used"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Probably will undo this change for now, as I'm just targeting Weekly Iteration in this PR."
    },
    {
      "prediction": "I don't think this should be used in tests.",
      "reference": "Unused parameter warning? How comes we did not catch that before? In any case please open another PR for this."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "I recommend move all openimage related logic to a new function"
    },
    {
      "prediction": "I think this is an external cgroup?",
      "reference": "We shouldn't have a bool for this. If there is a path passed, then we use it. Resource may or may not be empty."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `section_teachers.size` parameter.",
      "reference": "I like how you used the count on the translate call to handle this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need to do this from the outside, or is there a spot in the handler code where we can do this automatically? (I haven't studied it closely yet... just wondering if you've already thought it through or if it's worth taking a closer look)."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "[Checkstyle] INFO: Using the '._' form of import should be avoided - java.util._."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So, why everything is in memory but the permission backend?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are you sure it should be null and not an empty List?"
    },
    {
      "prediction": "I don't think this is the default dependency section.",
      "reference": "Unfortunately I think the assumption of \"empty\" means the default dependency section is not correct. For a project.json file the default dependencies section is a shared section between all the different target frameworks and our TargetGroup being empty may map to many different target frameworks so they aren't really equated."
    },
    {
      "prediction": "I think this should be removed in a future release.",
      "reference": "This test was verifying the wrong thing."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "pls pr a name change fro muon here too separately."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "nit: we can use `defer opts.spinner.Stop(\"Error!\")` after l.180 to make it slightly neater"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This is declared in the wrong block"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "In fact it would be useful for debug, i prefer combine them into one debug level log."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "We would need to localize them eventually too, just FYI"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It looks like the proto code needs to change the function name from set_name to set_type to be consistent."
    },
    {
      "prediction": "You may need to add a license to your project.",
      "reference": "I think we can avoid using this pattern for this use case."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Could you please change this to `#ifndef __linux__`? That's when we use our own implementation instead of `posix_spawnp`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: put the `&&` on the previous line so that a reader knows that there's more to the statement at a casual glance."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Technically the \"right\" variables to use would be the ones in `libgit/autogit_node_wrappers.go\", which define how the tlf types map to subdirs for autogit specifically. (They would have to be exported.) But this is fine too I guess, just a little dirtier."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `proposal_notification_email`?",
      "reference": "Should there be a template or something associated with this email? Right now it's identical to `notification_for_approver`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "i hope there is some extension in phpstan for this"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't store empty dictionary entries anymore: they bring no benefits, only trouble."
    },
    {
      "prediction": "I don't think this is the case when using scoped-enums, but it's not the case when using scoped-enums.",
      "reference": "Optional: This function is C++ specific and could be declared as `static`."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "we can't remove functions as that would introduce backward compatibility issues in our java client. So we should also have a function with the original arguments: ` public Roles getRoles(String domainName, Boolean members) { return getRoles(domainName, members, null, null); } ` For the Go client we don't have a wrapper so no option but to update your client code as necessary, but for java we have the wrapper thus we always maintain backward compatibility"
    },
    {
      "prediction": "I'm not sure why this is a hack, but I'm not sure if this is the case.",
      "reference": "I'd recommend keeping this in `warn_deprecation` and not adding an override of `warn`."
    },
    {
      "prediction": "I think this is a bug in `blitz build`?",
      "reference": "I think we should use a `blitz` bin instead"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Why not make the ``derived_vdims`` flag (or similar, ``validate_vdims`` maybe?) an explicit argument to ``validate``?"
    },
    {
      "prediction": "Should we return an error here?",
      "reference": "was it not possible to do this at the filter or porx driver layer? We typically try to avoid driver-specific things in the SDK layer"
    },
    {
      "prediction": "The \"License\" is distributed on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.",
      "reference": "please update the year. it can be setup in intellij template."
    },
    {
      "prediction": "I think this should be removed in a future release.",
      "reference": "what's the use-case for this?"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "nit: `as_index must be an boolean` -> `as_index must be a boolean`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "What is the goal of that method ? And what are `$currentVersion` and `$newVersion` ? Are they Thelia or Module version ? :)"
    },
    {
      "prediction": "I don't think this is a real error, but it's not a real error, but it's not a real error.",
      "reference": "Is there an advantage to this vs setting `this.version` in the constructor? Cleaner this way, at the top?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `getLoginUrl` method.",
      "reference": "Fix for URISyntaxException."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would be good to UT this case"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `import/no-extraneous-dependencies` or `import/no-unresolved-dependencies`?",
      "reference": "Why we need to add this?"
    },
    {
      "prediction": "I'm not sure why this should be done here, but I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is ok to change since I believe that these were added just in main and not in public release."
    },
    {
      "prediction": "I don't think why this is needed?",
      "reference": "Not needed in this PR, just want to make sure people think about this (maybe make an issue)? This is a lot of strings in a row. It will be hard/impossible for someone reading the code to see that everything is in the correct position. I recommend creating a struct instead of passing seven strings in a row. A similar problem exists on most of the `MakeFoo(...)` style methods in this change."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "_jaw drops_ I would have sworn I wrote those lines. Good catch."
    },
    {
      "prediction": "Should we remove this?",
      "reference": "This needs to be tested."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `building_address` instead of `building_address` instead of `building_address`",
      "reference": "I believe you're missing the comparison after 'be'"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "move 103~105 to in front of 97?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Lots of unnecessary imports left in this file."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Does this actually produce different code?"
    },
    {
      "prediction": "I don't think this.blur() is a function, but it's not a function.",
      "reference": "This should account for whitespace. Simply putting `.trim()` on the attribute value should do."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I don't think we need these. Simpler just to put `routetable.TargetType...` inline below."
    },
    {
      "prediction": "I think this is a bug in aws-cli.",
      "reference": "Nested if statement. You can merge both statements nested together to create one"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Nitpick: add a space after the comma. Also, we should consider that the format of the version could change in the future so we could get something that is not a parsable integer."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For your reference in future, I sugguest to use the `ASSERT_*` family."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "no need to import `fmt/format.h` here since the `KimInit` class is derived from `Pointers`. Any class derived from `Pointers` can assumed that `lmptype.h`, `mpi.h`, `cstddef`, `cstdio`, `string`, `utils.h` and `fmt/format.h` are already included through `pointers.h`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can we have prefix of `OPENEBS_IO` e.g.: `OPENEBS_IO_INSTANCE_NAME`"
    },
    {
      "prediction": "I don't think this is a problem with the `GetOrCreateRootNode` function.",
      "reference": "Might as well fix these bare returns by making them `return errors.New(...` directly."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "we can use import here"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "thx for removing these"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I snuck this one in as well as checkstyle crashing (on files from resources) caused an unfinished xml to be written, and it wasn't obvious where that XML was"
    },
    {
      "prediction": "I think this should be a good case.",
      "reference": "How is this different than \"good case\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "the last parameter name should be `serviceName` as is in the implementation  "
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure if this is the case.",
      "reference": "@ftomassetti - okay, this is a little meh."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Note, changed initial capitalisation of this for consistency. Can do it the other way around too if that'd be better. :wink:"
    },
    {
      "prediction": "I'm not sure if this is a `window` object.",
      "reference": "hey, aren't we supposed to be passing in two parameters here?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "please keep alphabetical ordering :)"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Selenium must compile against Java 6. Revert this line."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "what is that `\"\"`, the adapterType? can you add `\"\" /* adapterType */`... in other places as well... might be cleaner if it's a pointer or some varargs at the end but don't have any strong preference.."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "This check is a little odd, and will still mess up with empty strings `''` because empty string is falsy. Can we change this to `|| _this.getValue(path) == null`?"
    },
    {
      "prediction": "I don't think it's a `tabindex` attribute, but it's not a `tabindex` attribute.",
      "reference": "Just a minor suggestion: If you `parseInt` when you access the attribute then you shouldn't have to do it twice in the ternary."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This change in particular is strange. I'm not sure why it would now be necessary. The previous default would've been true, and the default behavior without a new net-ssh version should be unchanged."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is that? Should be redundant as the default value exists."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are all fields beginning with \"Debug\" automatically `;local` ? (I guess so, but just checking.)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "While I think it makes sense to update the mapping programmatically, I don't see much value in exposing it as part of the table API. We want to keep the Table API small, so if we can handle this by using a separate API that consumes and produces JSON, then that is preferred. Also, we may have more than one mapping in the future, so keeping this decoupled also helps out for those use cases. For now, let's build a utility class to perform these updates. We can always add this to the public API later if we choose to."
    },
    {
      "prediction": "I'm not sure why this is a bug in SsmpGlobals, but I'm not sure why this is a bug in SsmpGlobals.",
      "reference": "We would want ssmp to wake up every 3 seconds if there are no other requests to it and do some cleanup tasks. So, it is not clear why do you want to set this to 0."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this really necessary? I would expect these types to be included with the loop below."
    },
    {
      "prediction": "I don't think this is a bit weird.",
      "reference": "You could do span<byte> and it's magic of typecast to int for better efficiency"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `cssRule.style.transform` or `cssRule.style.webkitTransform`?",
      "reference": "Looks like you've covered `-webkit-transform`, but what about `-ms-transform`?"
    },
    {
      "prediction": "I think this is a bug in MvvmCross.Droid.Support.V7.RecyclerView.",
      "reference": "Is there something missing from the message here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the command line, but it's not the right thing to do with the command line.",
      "reference": "Hmm, what does this syntax mean?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "should this be callerTypeTask?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Currently update is set as @plan.editable_by?(@user.id) Which one is the correct behavior? I can see a case for only owners/co-owners to be able to set visibility, test status, and other plan details"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Maybe make it configurable? Or store the actual level index in DB, making this binary search obsolete?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: this file doesn't need to change. Can you revert this to avoid git conflicts?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `googlesitekit-dropdown-menu__icon-menu` or `googlesitekit-help-menu__icon-menu` and `googlesitekit-help-menu__icon-menu__icon-menu` and `googlesitekit-help-menu__icon-menu__icon-menu`",
      "reference": "There's no reason for this to be a callback now technically but as per our tech decision, we want all handlers to use `useCallback` now"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This isn't strictly part of this PR, but could you move `multiSigString` from `crypto/multisig.go` into this list of `HashID` values? Now that we have other things being hashed into addresses (specifically, these new logic addresses), it's important that the hash input for multisig addrs is domain-separated from logic addresses."
    },
    {
      "prediction": "I don't think this is a bug in the graphite.worker_pool.pool, but it's a bug in the graphite.worker_pool.pool.",
      "reference": "nit: you could have named it just \"TestCase\" (if django's TestCase was imported differently)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `page_ranges` option.",
      "reference": "the bridge here isn't defined as an accessor / reader to try mask it better. So you need to directly call the iVar `@bridge` here."
    },
    {
      "prediction": "I'm not sure if this is a special case.",
      "reference": "All the callers of `ExtractSomeIfAny`, always pass `true` to `synthetic_value`. Can we get rid of the extra argument?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the config file?",
      "reference": "Better to use the absolute path."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "this is 16 hours, is that enough?"
    },
    {
      "prediction": "I don't think `err` is a `nil` error.",
      "reference": "  removing boilerplate. You could also add a `StartSpan` with varargs to inline string attributes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you replace these single letter variables with full names?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "At first I wasn't sure, but now I think I'm sold on making PrepareRequest an action over adding a state object to the context."
    },
    {
      "prediction": "I'm not sure if this is a version number, but it's not a version number. I'm not sure if this is a version number.",
      "reference": "Would it be too greedy to preg_replace `VuFind (\\d+\\.?)+` with `'VuFind ' . $this->to` anywhere in the string? This would update something like 'Finna (VuFind 7.1.0)' as well. Just a thought, please disregard if you'd like to keep it as is."
    },
    {
      "prediction": "I think this is a problem?",
      "reference": "BTW for brevity, you can remove `getZkStateReader().` here and elsewhere since ZkController has a convenience method for the cluster state."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If there are no manifests, then entries should be `CloseableIterable.empty()`, not the manifest iterable. That doesn't need to be closeable."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this class should be named `ArrayInitializationVerbosenessTest` to work"
    },
    {
      "prediction": "I'm not sure if it's a Hash?",
      "reference": "Do we want to allow users to disable `console` as well? The schema currently says that it only permits a hash for `console`."
    },
    {
      "prediction": "I think this is not working. I think it's not working.",
      "reference": "It would be very helpful to describe succinctly either inline or by linking to an issue going into depth why each test is not working. If we merge like this your knowledge of what is going on is lost and other people in the code need to do a ton of reading before understanding when/how/if we should unskip."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "As this is a `useEffect` this could be a cause for concern! Note that `useEffect` re-runs when a dependency changes **not** when a dependency is truthy (the previous code does look a bit like it's expecting that)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we be doing this with `make_unique` or something?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "we don't want to set default values for this. Since it is the actual email, we want to make sure we are always passing in the `user` and `proposal` . we have a default value of `nil` for modifier because sometimes will update a proposal via `rails console` in which case there will be no recorded modifier."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `go/parser` and `go/loader` and `go/ssa`?",
      "reference": "Yes this import was in the wrong place, but should ideally be in the first list of imports (among `go/build`, `go/token`, etc.). You may move it there, or just revert this change as it's actually unrelated."
    },
    {
      "prediction": "I'm not sure if this is a bug pattern.",
      "reference": "It's unnecessary to duplicate the `name`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `unlink` event?",
      "reference": "this was a mistake when adding phpstan strict plugin"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Nit: I think it should be `to handle` here."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Please don't make unrelated changes or let your tools make unrelated changes."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "`numAccounts` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the plugin manager.",
      "reference": "Is the ID correctly normalized at this point?"
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "if 0 is a special constant meaning \"no limit\" let's make it a constant and name it correctly :)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Curious about the reason behind this change"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "wait, i thought the cborstore was for state tree?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This logic is now duplicated here and in `_delete_temporary_files`... Maybe do it all at once - find temp files, delete them, and fix the logical keys?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "How about name it with NullResponseTypeProcessor"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe `Log::Fatal` here? `[LightGBM] [Fatal] Check failed: feat_is_unconstrained at ...` (and kernel death in case of Jupyter Notebook) seems to be not so informative and user-friendly."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Not sure I like the name ``_apply``. Even though ``_process`` is supposed to process elements already, how about ``_process_element`` which processes elements, *excluding* Overlays/NdOverlays."
    },
    {
      "prediction": "I don't think this is the default value for the node role.",
      "reference": "Let's use this constant when ASG is created as well (currently hardcoded)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Oh is `bucket` actually higher cardinality than `eventname`?"
    },
    {
      "prediction": "I think this is a bug in PyQt5, but it's a bug in PyQt5.",
      "reference": "You can't rely on QtWebEngine being available - but why do you need to import this here at all?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "How did you determine these - and how can we be confident that nothing is missing?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "What is this page going to do that is different than the products index we already have?"
    },
    {
      "prediction": "I don't think this is a bug in Selenium.",
      "reference": "Couldn't you just write this as an if/else or a guard clause like on line 87? Just seems a bit weird doing this conditional assignment for essentially an if/else."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `s3_options` key.",
      "reference": "Is this intended to be here? Seems it belongs to a different PR."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "These changes, while harmless, were no longer needed with newer versions of System.Console thanks to @ianhays"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Umm... this isn't relevant to this PR"
    },
    {
      "prediction": "I don't think it's a bit of a hack, but it's a bit of a hack.",
      "reference": "While All make some sense here it doesn't make a lot of sense in the SkipOnFramework context. I wonder if we really need to expose anything more here. You can just blindly use 0."
    },
    {
      "prediction": "I think this is a bug in the Cobra project.",
      "reference": "Actually, this is not correct. Package `cmd/bee` doe snot have any notion of commands or even libraries used for them. It is as simple as possible, just calling the function from `cmd/bee/cmd` which actually implements commands."
    },
    {
      "prediction": "I'm not sure if this is a `route` method, but it's not a `route` method, but it's a `route` method.",
      "reference": "This change is causing tests to fail because users sits at `/app/users`, not `/app/admin/users`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Could you provide more information on what exactly each of those three options do?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `TraceFilePath` property?",
      "reference": "Why this line break?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We're importing this twice with different aliases."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We should avoid adding a pandera dependency to Dagster itself."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Can be replaced with `org.jkiss.utils.ArrayUtils#add`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "While we're here, this line (and a few others) should be `customThreadPool.submit(() -> IOUtils.closeQuietly(overseer);` I have no idea why we're creating a collection and a stream for a single object."
    },
    {
      "prediction": "I don't think this is a good idea to use the `managedIdentityClientID` and `managedIdentityResourceID` as well, but it's not a good idea to use the `managedIdentityClientID` and `managedIdentityResourceID` as the `managedIdentityClientID` and `managedIdentityResourceID` are the same as the `managedIdentityClientID` and `managedIdentityResourceID`",
      "reference": "Should these restrictions also be reflected in the API docs?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What about the request headers if someone uses `request_header`? :thinking:"
    },
    {
      "prediction": "This is a hack to make it easier to do with the `--domain-filter=%s` option.",
      "reference": "Verify that external-dns allows setting this parameter multiple times (that it's not \"last one wins\")."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Maybe 2 host/ip values could be used in the example?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "We're only testing `RateLimiter.Allowed(Span)`, so I think we can use a mock `ITraceContext` instead of a real `Tracer` or `TraceContext`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "IMO, this is the wrong way to associate a model with a trainer... Why the string when you actually have a trainer object?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Wondering if we can directly put types here & for other similar ledger_processor items like rai::block_type::state"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "As `DeleteFiles` is not only used for prune this function deserves its own file. Maybe something like `delete_files.go` or `parallel.go`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It should be simplified character. `` -> ``"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I am pretty sure it breaks the visitor pattern, visitor should have no knowledge about the structure of what it is visiting or control over visiting mechanism"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "'A' instead of 'An' here"
    },
    {
      "prediction": "I think this is the default timeout used for the long poll.",
      "reference": "Can you flip it back (here and in other places)? It is more natural to represent \"10 seconds\" as `10 * time.Second`."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Why was this necessary? You should just use the `dask_classifier` defined below this. With this change, you'd only be doing the local predict on arrays each time, but we want to test on all of DataFrame, Array, and sparse matrix."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "To me, this is sort of weird to have a completely separate page for this. Can we extract the different stuff (github, videos, downloads) presentation from the top of `app/views/purchases/show.html.erb` and reuse it on this page. I worry that we'll change things with fulfillment or copy and have to change it in multiple places."
    },
    {
      "prediction": "I don't think this is a bug in this package.",
      "reference": "Please revert the lines above. Not touching unrelated code keeps the git history clean."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`short_version` and `version_info`"
    },
    {
      "prediction": "This is a hack.",
      "reference": "This is supposed to be `status`. Why did you change this?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I will change all of these at some point next week."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I made this change because, while trying to debug, in Visual Studio, the `IntegrationSignatureTests`, this property getter was hit and interfered with my ability to complete the debugging."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: `\"Unexpected error while calculating: unable to convert %T to %T: %v\"`"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I'd actually recommend not putting this in the `SampleConfig`, it's intended more for properties that are inherent of the discovery format. Add a method `getSampleAppName(String apiTypeName)` to `SampleNamer` and override it in the language specific `SampleNamer`s if needed. Then assign it in the transformer."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Do we need to export these new functions? I thought the plan going forward was to keep util imports separated to make circular imports less likely and possibly do better chunk splitting. Since only new code references these files, we can scope the import to the specific files."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Rails will autorequire `acts_as_editable` once it encounters the constant `ActsAsEditable`. Thus if we move `ActiveRecord::Base.send :include, ActsAsEditable` from _acts_as_editable.rb_ to this file, the require line will not be needed anymore. Instead of requiring the file ourselves, we will let Rails do it for us. This fix will also remove the need to explicitly require `acts_as_editable` in _mock_active_record_base.rb_."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `methodName` and `upperCamelMethodName` and `upperCamelMethodName`?",
      "reference": "I think we should name this `grpcMethodName` or similar. That is what this refers to, right? The fact that it is upper camel is an implementation."
    },
    {
      "prediction": "I don't think it's a valid name, but I don't think it's a valid name.",
      "reference": "What if .. appears, but not as the first character, eg \"errors/../../../../../../../../../../../\"?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Thanks, this should make things a bit easier for people who pick up the codebase but aren't a `curation center`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "why not removing it?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "same nit here: maybe word as - \"disables validation of the temporal cluster's server certificate\""
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Nit: other statements use all caps for SQL reserved words. Should this be `SHOW TABLES`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need this? isLuaIdentifier() is used not only in extract_next_token() but also in extract_prev_toke(). I wonder whether the change for isLuaIdentifier() has an impact on extract_prev_toke() or not. If you are not sure, keep isLuaIdentifier() as is. If you are sure, could you write your conviction to the commit log."
    },
    {
      "prediction": "I don't think this is the default MTU.",
      "reference": "This line should actually be: `if c.KubernetesProvider == config.ProviderAKS && c.Wireguard.EncryptHostTraffic {` because we only need to tweak the MTU like this on AKS."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do we need to change this flag as well?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Including the source twice here makes the filesize jump to 432kb. Is there any way to minimize repeating it?"
    },
    {
      "prediction": "I'm not sure if this is a WebDriver instance.",
      "reference": "This should only be sent if the driver is speaking to a W3C conformant remote, so we need an if-condition check like we have in the Python bindings."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Only one line of code? What a simple issue!"
    },
    {
      "prediction": "I think this should be a function that returns a float64, but it's not a function that returns a float64.",
      "reference": "Conceptual question: why do history and matching need throttler at all? Shouldn't throttling to be handled on FE only?"
    },
    {
      "prediction": "I don't think this is the case where we don't want to reprocess the CNP.",
      "reference": "Would this be possible: `addCNP` has already processed the CNP to an internalNP, just hasn't added this internalNP to the `internalNetworkPolicyStore`. In this case, `reprocessCNP` will skip processing this CNP and `addCNP` will just add the \"old\" internalNP to `internalNetworkPolicyStore`."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "Minor: you can access `current_user` in here directly - don't need to pass it in. Unless you prefer passing it explicitly?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "What is the purpose of `&` on this line?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "See above, the `isValidWebDataStreamID` implementation from before is actually correct. What we need here instead is a new `isValidMeasurementID` function."
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "Should be an error... it is important for the admin of the server attempting to create the leafnode connection to see the error asap."
    },
    {
      "prediction": "I don't think this is the case for the 'unselected' state.",
      "reference": "Could you split these conditions up over multiple lines please."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we can just change this to `Split` instead of `SplitN`. I don't think we need to limit the number of parts in the tag."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So this is actually a mistake that I introduced without realizing it, and have known would need to be fixed when we get here  . The format of the ports directive is \"host:container\". We only want the host port to change, not the internal container ports. The ports variable probably needs to be a map which maps external -> internal ports."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "An alternate approach would be to always initialize shardInfo with a dummy (non-nil) value, which could protect against other uses before it's initialized (I couldn't find any though). But I can change it to do it that way instead."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Maybe we can just put the entire `DirEntry` in here? I can imagine it might be useful for debugging to get the block ID/refnonce, encrypted size, key gen, data version, etc. What do you think?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For the commit message: The paragraphs seem to be out of order? The `Would not work because` refers to the stuff before, but there is a `This may seem pointless, but` in-between."
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's a string, but it's not a string, but it's not a string.",
      "reference": "Why did you remove these packages from the prelude, will your new functions not work without this change?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "We'd better reserve enough space before using kvKeys to avoid extra malloc."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "would it make sense to return empty or error if label doesn't exists?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `rimraf`?",
      "reference": "Don't penalize everyone with 250ms delay b/c some machines have problems."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Probably want a space after the second %s?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This seems like an internal error still?"
    },
    {
      "prediction": "I'm not sure why this should be the case. I'm not sure why this should be the case.",
      "reference": "Line is too long. [94/80]"
    },
    {
      "prediction": "I don't think this is a problem with the user or generated by the Antrea Controller, but this is not a problem with the user or generated by the Antrea Controller.",
      "reference": "out of curiosity, why creating another struct to wrap it?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "discipline vs. Discipline? Not sure of which is correct. Also not sure if there is already an existing string const."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I believe this will break common resources, as they are defined in a common file, but must generate classes in service-specific namespace, so using protoFile to determine package of the generated class would not work, because common_resources namespace does not match service namespace."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "How about `SPARK_DEFAULT_SERIES_NAME`?"
    },
    {
      "prediction": "I think this is the default value for the default value, but it's not the default value for the default value, but it's the default value for the default value for the default value.",
      "reference": "The other properties are in `commit.status-check`, not `commit.status-checks`. Could you remove the extra `s`?"
    },
    {
      "prediction": "I don't think this is the case for the unified topology.",
      "reference": "Side note: I'd love to see more of these fields exposed on configuration."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "In the case of accounts generated by API clients, what name gets put for the `inviter_name` or `invited_by` record?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think this class is only relevant for updating the QbftConfigOptions based on the transitions config, so probably not."
    },
    {
      "prediction": "I think this is a bug in Nethermind.JsonRpc.",
      "reference": "what is the number thrown by Geth?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This would still crash on malformed database connection string like \"test\""
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "it is not an interface, maybe we can move to another package?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same here. Can we use `this.instance.getSettings()` to get `tableMeta`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure whether this validation is useful."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `yank_text` attribute.",
      "reference": "Various things to note here: - Why would `question` ever be falsey (or `None`) here, i.e. why the `if question`? - Why would `question` ever not have that attribute? You set it in `Question.__init__`, so that check does nothing at all (and generally, `hasattr()` should be avoided if possible). - Why do you want to yank `None` (what does that do?) rather than e.g. show an error if there's nothing to yank?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "If this is needed for testing, you should use `pytest --log-cli-level=INFO` instead."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should drop ipify in all places i guess"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Add explanations around these variables - what do they mean, how they should be configured, etc."
    },
    {
      "prediction": "I don't think this should be called on app init?",
      "reference": "One thing tho - I would really appreciate any advice on where to move this to, so that it's called on initialisation of the website."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "To much tabs here (1 tab)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is not maintaining retention time for logs as we are deleting only 1000 entries and we might end up with huge number of rows spanning over multiple months over a period of time if the cluster generates more rows as we are restricting ourselves to delete only 24k rows/day. Like I pointed out earlier a better would be to probably run this clean up every hour with some batch_size in a loop while there are records to be deleted(i.e older than 12 weeks) and committing each batch."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "I don't like this helper func :-). Yeah, definitely don't like."
    },
    {
      "prediction": "I don't think this is the case for the `google-site-kit/v1/modules/pagespeed-insights/data/pagespeed` module.",
      "reference": "Same here. This should remain unchanged. Please, add it back."
    },
    {
      "prediction": "I'm not sure if this.s.options.ignoreUndefined is set to true.",
      "reference": "@kvwalker should this method have `ignoreUndefined` supported as an `option`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "we dont use a `sugaredlogger` anywhere else in clutch, just curious why were using it here?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Not evident from looking at this diff but the queue is already being cleared four lines below."
    },
    {
      "prediction": "I don't think this is the case for the compact-cert-sender address, but it's not the case for the compact-cert-sender address.",
      "reference": "Why is this a 'transaction' and not in the block header?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This doesn't fit the abstraction level. Should we have a property bag for extra stuff?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Looks like it is pretty easy to miss it when adding new files under `ci`. Hopefully, this doesn't happen too often."
    },
    {
      "prediction": "I think this is a bug in p2ps.p2pService.",
      "reference": "do we really need the `Ready` call if startup fails midway?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You can avoid changing the code if there are parameter defaults. right ?"
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "I wonder why the newline disappeared here? I guess we'll merge and see how SauceLabs fares across the supported browsers."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I know this is legal, but I prefer we put brackets on our calls"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We keep who wrote the code anonymous."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `currency` property.",
      "reference": "Two things to make the code more error-proof and simplify it: 1. To be safe, this should be: `! isUndefined( decimal ) && ! isUndefined( decimal.value )` 2. The other clause that you changed below can be combined with that since `decimal` isn't used anywhere else, and so there's no point to re-check whether it's not undefined. In other words, this should become: `! isUndefined( decimal ) && ! isUndefined( decimal.value ) && 1000 > number`, and then you can remove the `decimal = decimal.value` assignment and replace it with line 146 (assignment of `readableNumber`)."
    },
    {
      "prediction": "I'm not sure if this is the case for a single transport.",
      "reference": "Wouldn't composite outbounds compose the transport, such that it would still be represented as a single transport?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: there is no need for a new line here, usually we tend to put an object creation and its deferred deletion next to each other. It helps not forgetting about the cleanup."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Feel free to use the full notation with my email address: `Maxime Steinhausser <maxime.steinhausser@gmail.com>` :smile:"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This was unused across the codebase"
    },
    {
      "prediction": "I think this is a bug in JetStream.",
      "reference": "Should we put in which account we were trying to look up?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "either SUPPORTED_TYPECLASS or supported_typeclass. Camelcase only for class names."
    },
    {
      "prediction": "How to do this?",
      "reference": "This is not going to work. You need to add a migration to the database."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Should these methods be renamed in this PR?"
    },
    {
      "prediction": "I think this is not a valid instrument name?",
      "reference": "we need to include the `metricStreamName` which is invalid, so users know whats causing the issue."
    },
    {
      "prediction": "I don't think this is the right thing to do with the load context.",
      "reference": "Please run Platform tests `DiaSessionTests`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This is debug-build-only: we want a release-build notice. SYSLOG takes the name w/o the MSG and no _STRING. Args are via events.mc specifiers."
    },
    {
      "prediction": "I don't think this is a problem with the `directConnection` option.",
      "reference": "is it possible to have both forms here? I was hoping we wouldn't be introducing more cases where we had to check the upper and lowercase version of URI options."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does the name suffix hardcode something? Not clear how changing the name fixes this."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is undispatched same as queued? getQueuedFlows?"
    },
    {
      "prediction": "How to do this?",
      "reference": "See above, same for all similar cases below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this done twice?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This sync can ensure that the condition of the child node is consistent with the parent node, but I still don't understand when the child will be overwritten, and this behavior is not what we expected?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was renamed to avoid any confusion with the more general case of debugging via `plz debug`"
    },
    {
      "prediction": "I'm not sure if it's a string, but I'm not sure if it's a byte[] or a string.",
      "reference": "String valStr = (String)val; valStr.substring(0, Math.min(valStr.length(), prefixLength)) Make it clean."
    },
    {
      "prediction": "I think this should be a `void` type, but it's not a `void` type.",
      "reference": "Sorry, this still makes no sense.. the value of any union or enum is simply a name integer constant, it has nothing to do with the `BASE_TYPE_` enum. This value should be `0`. In particular: `Every union has the NONE field, which always has value 0`."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Looks like getAzkabanURL() is added after concrete Alerter (Emailer)::getAzkabanURL(), so that Override annotation is needed."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "The above 3 lines can be written as: `mask = segms[i].astype(bool)`"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core/pkg/util/byteutil. This is a bug in iotex-core/pkg/util/byteutil. This is a bug in iotex-core/pkg/util/byteutil.",
      "reference": "File is not `gofmt`-ed with `-s` (from `gofmt`)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Thought it's good to have this logged down so that we can check the used value in the logs."
    },
    {
      "prediction": "I think this should be a `bool` or `bool`?",
      "reference": "I don't think you can call this optional unless it's a pointer - remove this?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@naofum please use `isEmpty`method instead"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i think this is unrelated and needs to be reverted. need to discuss at sync."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Are we eventually moving those type interfaces from plugin project to datatype project? If not, then we'd have a dependency from core onto plugins, which seems a little counter-intuitive to me."
    },
    {
      "prediction": "I'm not sure why this is a `syncIndexes` function?",
      "reference": "Love how we can finally use async/await in the codebase."
    },
    {
      "prediction": "I don't think this is a good idea to do with the `update_existing_accounts` option.",
      "reference": "Very minor: this line could be moved to a more narrow scope, inside `if (!representative.decode_account (representative_text))` Other than that, LGTM"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "when is this consumed? I'm probably missing it but I can't find it right now"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is a rollup.",
      "reference": "I think we also need to add the rollupGroupExprList() to the cache key. If we rebuild the list above from a ValueIdSet on line 418 above, it is probably going to be in the same order, regardless whether it was ROLLUP(a,b) or ROLLUP(b,a)."
    },
    {
      "prediction": "I'm not sure if this is needed?",
      "reference": "can use `getParamTypeName` instead"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `newValue` parameter?",
      "reference": "Why send the parameters? They're accessible directly from `$this->request` so there's no need to inject them in the method"
    },
    {
      "prediction": "I don't think this is the default behaviour.",
      "reference": "Tiny nit: I would prefer `not selected_file` or `len(selected_file) == 0`, as if choose_file starts returning, for example, tuples instead of lists, this won't break."
    },
    {
      "prediction": "I think this is a bug in etcd.",
      "reference": "How will this code behave with hostnames that contain hyphens?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think this is redundant since \"NullForEmpty\" already calls \"Trim()\"."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Change this to IDs too?"
    },
    {
      "prediction": "I don't think this is a bug in the spec.",
      "reference": "private static final, and it should be located in raidsoverlay, as it's not needed in the plugin. also the name could be a bit better, DC_SCOUT_RAIDS or similiar."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "attr_value is 128 bytes?"
    },
    {
      "prediction": "I don't think this is the right thing to do?",
      "reference": "if it's unpredictable - why uppercase it at all?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please remove all these debug prints. It doesn't look good."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Consumers of this interface should not be required to provide `sampleHeight`. This should be an expected consensus parameter."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't believe this is the right fix. If startTime comes after closeTime, then it means some other event triggered invocation of this code path like workflow timeout. In this case we should still try to fire the cron on previous value so we should just return start the delta between startTime and closeTime immediately."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Not sure if we need tag here, it is an implementation detail in portworx that isn't exposed in openstorage"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "I wonder if it would be cleaner to refactor all of this similar to the SolrMarc driver, so we have a property with Summon field names associated with types, and we iterate through it in a loop... that way we don't have to repeat the loop code four times with different variable names."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Need the `solrClientCache.close();` further down in the method be removed since a shared cache is now used?"
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's not a string.",
      "reference": "according to the PR (schema changes?) these 2 field should be removed?"
    },
    {
      "prediction": "I don't think this is a problem with the `StressChaos` field.",
      "reference": "Panic here if `exp.Target.StressChaos.CintainerName` is nil."
    },
    {
      "prediction": "I don't think this is the default behavior.",
      "reference": "This allows for some hacks like returning an iterator that matches more docs than the scorer. I liked the previous approach that returned an iterator better."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "Aren't there already logs for this from the underlying file system implementation?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It would be good to have a test in here that demonstrates the new munge functionality; I can help set that up if you're not sure how."
    },
    {
      "prediction": "I'm not sure how to do this with the `max_retrials_to_get_pods` parameter?",
      "reference": "`retrials` isn't the word you intend. I think you mean `retries` and to that end, can the var name just be `max_retries`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing.",
      "reference": "Value in product should contain 255 characters or less."
    },
    {
      "prediction": "I think this is a bug in the future. I think this is a bug in the future.",
      "reference": "line is 133 characters (from `lll`)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `custom_options_file`?",
      "reference": "since we're calling the file .rspec-local, I think we should rename local_options to project_options and use local_options for .rspec-local - WDYT?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `connection_config.merge(adapter: connection_config[:http_adapter])`?",
      "reference": "Will we want to refactor this when we drop rsolr 1.x support?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "should this really be multiple IPs?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Hmm, is that partial used in multiple places? Maybe we can just move that file in here."
    },
    {
      "prediction": "The \"License\" file is distributed under the Apache License, Version 2.0 (the \"License\" file).",
      "reference": "Should be 2014-2016"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like my fault for sure in trying to handle international inputs regardless of locale. I think the correct fix is actually to get rid of TrySplitColumns and use ParseDsvFields instead. It is what gets used in the end, and it already has logic for dealing with quoted fields."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "similarly here, are the these cursors not being closed when the client is closed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Or maybe `func(args ...string) Policy` to make it dynamic in case of any future policy that may require more than one args."
    },
    {
      "prediction": "I think this is a bug in the journals server.",
      "reference": "Should this happen even if the above failed?"
    },
    {
      "prediction": "I don't know if this file is needed.",
      "reference": "Please dont change this ."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There is a strange $b that looks wrong."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `speakEntry` and `childControlCount` in the `list` section.",
      "reference": "Is it still important to have `speakEntry` here? It is checked before this value `containerContainsText` is used in the \"General\" section."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It is `$JAVA_HOME/bin`, not `$JAVA_HOME`, which should be added."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Should move this to within the `#else` block as it's only used there."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `addProductToCartByName` method.",
      "reference": "is this a common rule to wait one extra second after ajax? I'm thinking about moving this extra wait into waitForAjax method."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `$this` object.",
      "reference": "Maybe you can correct the typo \"if\" too :)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I'd prefer a name less chat-specific, since later on we could have other app types that want the same behavior. Maybe `IdentifyAndAllowTrackBreaks`?"
    },
    {
      "prediction": "I don't think this is a bug in Python 2.X.",
      "reference": "I think I was involved in writing that caster, but I never fully understood the `import_mpi4py` thing. Why is importing mpi4py still necessary at that point? I would think if the user is passing a communicator from python code, they must already have imported mpi4py themselves, or does that not propagate through into the wrapping layer?"
    },
    {
      "prediction": "I think this should be an error?",
      "reference": "This seems like a more interesting change. Maybe we should re-name the PR"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Nit: implement the methods for these interfaces explicitly in this file for consistency. It can be passthrough."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Not directly related to your PR, but I think here we should create a Type enum (MAP, ARRAY, PRIMITIVE) instead of having 3 flags."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you want this to be a stack variable? The work method might return at any time (example: when the parent queue fills up) and then get called again, which would cause this variable to become false again. I'm wondering if this variable should be a member instead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You could reserve a const space to save the extra computation."
    },
    {
      "prediction": "I think this is a bug in the coreclr/runtime/src/libraries/System.Private.CoreLib/src/System/IO/Path.cs file. I think this is a bug in the coreclr/runtime/src/libraries/System.Private.CoreLib/src/System/IO/Path.cs file. I think this is a bug in the coreclr/runtime/src/libraries/System.Private.CoreLib/src",
      "reference": "Did you consider adding rooted paths like `C:\\ProgramData` and paths with flipped separators?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "does this line cause a panic if it is above the if condition ?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe `LibraryDetailsPanelType` would be clearer."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "minor nit - add \"persist-filesystem\" and \"persist-directory\" into commit message, as its something people may search on (maybe applies to a few other commit messages)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I verified offline with @jeremyg-lunarg this should be removed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should be removed? If not, typo in incldued_wf"
    },
    {
      "prediction": "I'm not sure why this is the default variant.",
      "reference": "Sorry for the delay on this! It looks like Circle CI isn't running tests on some of the PRs, but this doesn't look like it would work   I might be missing something, but are the tests all passing locally?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do you think the godoc should mention that all delimiters will be suffixed with `/`?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `SessionStore.get().isCurrentSessionPrivate()` method.",
      "reference": "what if I want to load my own, a different, data URI in Private Browsing mode? I do this often on desktop (e.g., `data:text/html,&times;`). admittedly, I wouldn't expect this to be done by a non-developer, but this will certainly cause a minor bug."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I remember the sequence number 0 is kept for the data files for iceberg v1, so in theory the sequence number from delete files should start from 1. So setting it to 0 as the default value sounds correct."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "For all these MYSQL queries unsigned is required. I have tested again and without unsigned these queries are failing."
    },
    {
      "prediction": "I don't think this is the default state.",
      "reference": "Are there tests for this? What happens when you get to limit?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Whole thing could be collapsed to `data['config']['transport'] ||= 'local' if target.name == 'localhost'`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "maybe throw in `&& mServiceConnection.isBound()`, there are cases where the connection might die"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we add Istanbul with this first EIP please? (or as a separate issue)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't understand this change"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Let's allow translators for this string to be translated: `self.show_warning(_('Invalid Public key'))`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `role` attribute?",
      "reference": "This needs to work with `role=form` too."
    },
    {
      "prediction": "I'm not sure if this is the case for output values.",
      "reference": "This should be before the if on line 1028, which should turn into an else if"
    },
    {
      "prediction": "I think this is a bug in the spec.",
      "reference": "Not really introduced by this PR, but I don't recall why these have to be pointers, while `PodSelector` / `NSSelector` do not. Do you know the reason?"
    },
    {
      "prediction": "I think this should be a good idea.",
      "reference": "Is there a reason why we are ignoring the ackDelay if it would result in a value smaller than the min? Why not `max(sample - ackDelay, minRTT)`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `IEqualityComparer<SarifLog>`, but it's not the right thing to do with the `IEqualityComparer<SarifLog>`, but it's not the right thing to do with the `IEqualityComparer<SarifLog>`, but it's not the right thing to do with the `IEqualityComparer<SarifLog>`.",
      "reference": "Here's an example of how the files in the `NotYetGenerated` directory drifted out of sync from the generated files. When we made the equality comparers internal, we neglected to fix this one."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "nice. we should do this elsewhere too. We have a lot of repeated stuff in the policies"
    },
    {
      "prediction": "I'm not sure if this is a default argument. I'm not sure if this is a default argument. I'm not sure if this is a default argument.",
      "reference": "Small formatting thing, but can you remove the space before the semicolon?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Not new, but nit: _writeLeng*th*."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Our habit is to go ahead and put a description line (or more) in front of every function, not just non-test or exported functions."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Remove this file from the PR"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think that for cloud variables, the default value in the prompt should be the variable name without the cloud prefix; this is slightly different from the scratch 2.0 behavior, but I think would ultimately lead to less confusion. Proposing code changes below:"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think I would rather fish this interface through than use it as the basis for heuristics."
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack.",
      "reference": "Probably not worth making this line-ending change, since it is the only change to this file."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this the correct place for this assert? Does this routine rely on it being 64, or was this only for testing?"
    },
    {
      "prediction": "How to do this?",
      "reference": "No pb please"
    },
    {
      "prediction": "I don't think it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bigint, but it's a bit too.",
      "reference": "We need to add indexes here on both `subscriber_id` and `changeset_id` or things will quickly collapse as we build up subscribers ;-) What I would suggest is a unique index on `[:subscriber_id, :changeset_id]` which will also make duplicate entries impossible, and an ordinary index on `[:changeset_id]` for finding the subscribers to a changeset."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "use the context versions of everything, e.g. `PostMessageContext` and thread it through the functions. will save you a bunch of refactoring trouble later on."
    },
    {
      "prediction": "I think this should be a list of tuples, not a list of tuples.",
      "reference": "\"not to be used elsewhere other than\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Thanks for the contribution, @coolderli ! I also think the newPosDeleteWriter need the properties setting ..."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "These additions seem unrelated to this change?"
    },
    {
      "prediction": "I think this is the default value for this property.",
      "reference": "Could we move this to a class for Hadoop configuration properties, like `org.apache.iceberg.hadoop.ConfigProperties`?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "The related statements should also be deleted."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `policies` parameter.",
      "reference": "Shouldn't this line be removed?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Just move this into `const.py`. It already has similar stuff. Also, make it uppercase since it's a const."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Issue is that `currentMode = newMode;` is called at the end of the method. Passcode screen will come up, but since the activity thinks current mode is biometric check we don't check passcode when submitted."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "Need change it back?"
    },
    {
      "prediction": "This is a hack, but I'm not sure if you're using `rake secret` or `rake secret_key_base`",
      "reference": "Didn't we delete this file a while back because it isn't used but people think that it's a security vulnerability that it's checked in?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "nit: Looks like this can be removed now"
    },
    {
      "prediction": "I think this is the default CA, but it's not the default one.",
      "reference": "Can probably remove the lines above it too (L60-62), since ProvisionDefaultCA() makes sure the map isn't nil."
    },
    {
      "prediction": "How to do this?",
      "reference": "Do you think it's worth erroring out? It's likely that this is a configuration error that the user might want to know about?"
    },
    {
      "prediction": "I think this is broken.",
      "reference": "I think the functional test should not change here, this is probably a test in itself :)"
    },
    {
      "prediction": "I don't think this is a bug in the future. I think this is a bug in the future.",
      "reference": "Why this to be a public function?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `echo` command.",
      "reference": "I think we can remove the timing for export env vars"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "wrong import grouping"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There is a doubled semicolon ;)"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "I'm wondering why this isn't <openssl/md5.h>. Seems like one would have to copy the md5.h file into the source tree somewhere for this to compile cleanly. Maybe you meant to use angle brackets instead of quotes?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "shouldn't **call** return a boolean?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "We don't need to cast to client here. (well, from spell gem not AA etc) We should also make sure the charm is a casted spell before calling SendSpellBarEnable."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This is not an `id`. This should either be `invocation_time` or `invocated_at` to be consistent with what we are using elsewhere, and also to better rerflect the column's DateTime type. Also, within the context of this table, there is no idea of what `invocation` is. I know that `scanner` may not be future-proof, but we need to find something more descriptive. Perhaps one possibility is to call this `audit_time`."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "should the 'Receiver' be the clawback address in case of clawback transaction?"
    },
    {
      "prediction": "I don't think this is the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's the default.",
      "reference": "@ashishranjan738 -- Where are these consts used? in which pkg?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `:toctree: pythonapi/` and `:toctree: pythonapi/` and `:toctree: pythonapi/`",
      "reference": "The only change I would suggest is moving these lines back below the `templates_path` variable to keep the diffs smaller."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Having it above kept the block info in the cached changes, which could end up confusing things quite a bit."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "If the execute_task returns an `ExecutionResult`, the passing of a block would be unnecessary. Instead, the `ExecutionResult` could be presented to the user in some standardized way (iterating over the result of each node, etc.)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure why we make a new channel here. If we don't use this channel, how about creating it inside the `Connect`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There are two question here: 1. If you only modify lastLogId, but the `iter` is not modified, I really don't know whether we can succeed. 2. We will check the if the term has changed in `replicateLogs` (if rollback really happen, the term must have been updated), so I really doubt whether the problem should be fixed in this way. Or you could describe it in more details."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Hello @jDolba, I have reviewed your PR and I found one problem. `$step->getFormType()` can return `FormTypeInterface`. You cannot use interface as key for an array. Can you find some better way to fix this? Thank you."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "i was confused by keyword \"inventory\" here. my understanding is this starts the osconfig-agent which covers inventory lookup and package-management(correct me if i am wrong)."
    },
    {
      "prediction": "I don't think this is a string, but it's not a string.",
      "reference": "These are really meant to be the keys in the capabilities, not the keys of values within the capabilities"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `preact` and `preact/hooks` and `preact/hooks/setupScratch`",
      "reference": "This breaks tests on IE because this will import an `esm` bundle. For that reason `sinon` is available as a global in our test suite and never imported. The global is aliased to the proper `es5` file."
    },
    {
      "prediction": "I don't think this is the default value for the RTO alarm, but it's the default value for the RTO alarm.",
      "reference": "Maybe move all the Loss Recovery constants to a separate file."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this field is added so that we can find disk name by device name from attachments"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Unnecessary new line"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "First determine if the namespace already exists, so it's clearer that it's handling namespaces that aren't included in the `c.config.Namespaces`"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "What changed in the styles that means we don't need this?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This pattern should be applied to the other instance where NewtonsoftEscapeJProperty is used and you can remove the NewtonsoftEscapeJProperty method."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Something to mention in the next changelog/release notes. It will be good to get histogram working consistently with everything else."
    },
    {
      "prediction": "I think this is a bug in kubernetes.io.",
      "reference": "What does this contain? Is it PVC namespace or is it openebs?"
    },
    {
      "prediction": "I think this is the default value for the minimum data rate feature.",
      "reference": "Design note: Using local concrete data types on a feature abstraction makes it hard to generalize / replace. This is tolerable so long as this remains a kestrel exclusive feature, but we'd need a different design if this were ever moved to HttpAbstractions."
    },
    {
      "prediction": "I think this is a bit of a hack, but I don't think it's a bit of a hack.",
      "reference": "this will break R package, you should update the R files accordingly. BTW, the call state should be in the last argument."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't we throw an exception if the context is null instead ?"
    },
    {
      "prediction": "I think this is the default version of docker-compose required for ddev.",
      "reference": "These should both be const, not var right?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Rename the directory, match_costers -> match_costs"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think this should go in the model tests, since it is done in the resource. `PaginatedDeleteTest` seems more appropriate"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It would be better to just change RWD to throw IllegalStateException if you attempt to execute a command after quit (unless it's a second call to quit())"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Could we move this to an example test to allow the compiler to help us ensure it stays up-to-date in the future?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe we could update these to use $future and then check on stderr? that way when we deprecate stdout we can not have to delete tests."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Remove this since it always has to be set afterwards."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "These two tests were causing us to use too many goroutines with `-race` using the default block change size, I think due to prefetching."
    },
    {
      "prediction": "I don't think this is a problem with `fetch` and `fetch`?",
      "reference": "Is that `try..except` block really needed? I mean, when it could fail?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "If you only want to run a specific group of tests you can always use `.only` like `it.only()` or `describe.only()`. It may not speed up the globbing process as much as this change here :)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: I'd probably rename this to `BATCH_SIZE_RANGES`, to use a slightly more descriptive name."
    },
    {
      "prediction": "I'm not sure why this should be added to the menu.",
      "reference": "aren't these the wrong way around?"
    },
    {
      "prediction": "I'm not sure if this is a CoreContainer.",
      "reference": "Lets call this getConfigSetService and maybe rename the field now (or later)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Could / should we make these constants and give them a type?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "lets stick with lowercase for consistency."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "ordering of imports went wrong"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I think these can all be .name() to get the value we are looking for"
    },
    {
      "prediction": "I'm not sure if this is a function call.",
      "reference": "Is this a good place for these test cases?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Did you mean to leave the print statement?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "I would do `new BN(Interpreter.LOCKTIME_THRESHOLD)`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@ftomassetti I turned the tree walking algorithms into iterators so you don't have to visit every node when you only wanted a few, like for a `findFirst`."
    },
    {
      "prediction": "I think this is a bug in cadenceInternal.",
      "reference": "Need to add type name here to be compatible with proto string representation."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "This is to let people know that the tooling is doing something during a build. Please leave."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why is the principal changing here?"
    },
    {
      "prediction": "I don't think this is the right thing to use.",
      "reference": "Naming nit: let's use `AZURE_STORAGE_` prefix for consistency with the other ones."
    },
    {
      "prediction": "I'm not sure why this is a `Plugin`?",
      "reference": "I'm a bit confused. We have an actual `ProgressBar` Uppy React wrapper component that we are testing. Why do we need a mock for it?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `k8s.io/apimachinery/pkg/apis/meta/v1` package.",
      "reference": "can we use `github.com/pkg/errors`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I changed the name of the arguments here just to help make the code clearer."
    },
    {
      "prediction": "I'm not sure if this is a dynamic map, but it's not a dynamic map. I'm not sure if this is a dynamic map. I'm not sure if this is a dynamic map.",
      "reference": "I think either 'avoiding calls to the function' or 'to avoid calling the function ...' would be read better."
    },
    {
      "prediction": "This is a hack.",
      "reference": "@sfricke-samsung -- thanks. saves a few atomic ops which is always good :) The TODO is there to track that this object is storing *both* vectors of shared_ptr and plain pointers to the same data. The shared are to ensure scope, and the plain are for backwards compatibility with existing code that consumed a plain pointer vector (and some code that still does). That should be cleaned up."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with Nethermind.Monitoring.Config and Nethermind.Monitoring.Metrics, but I'm not sure if this is the right thing to do with Nethermind.Monitoring.Config and Nethermind.Monitoring.Metrics",
      "reference": "minor: typo (knowMetricsTypes -> knownMetricsTypes)"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This adds a case-insensitive flag to the type in the RangeSpec, but I don't think RangeSpecs are written to handle case-insensitive comparisons. Take a look at the methods that deal with comparisons when building RangeSpecs, in file Range.cpp. So, I think you would have to do one of two things: a) disable the RangeSpec transformation for case-insensitive comparison operators (the easy way) or b) change the RangeSpec methods to handle case-insensitive comparisons."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "I would throw an exception if the type is not solved"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "if remove `dt.skipLoad` - then this tests will run. You probably mean opposite?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I feel like we do this in a lot of places should we move that out into its own PR?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Already asked you in Matrix, but I'll do it here again so it can be discussed publicly. Why?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "I think here should be a comma before remove, in all the cases"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Single quote is used by default in this project."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "S1023: redundant `return` statement (from `gosimple`)"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "`ctx` is unused in Close"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I'm confused. This exception is thrown when `HeurekaCategory` is not found in database. But this exception extends Http exception. Why? What has database search common with http? If the only reason is that it is the same in the whole project, then fine. But then we have even bigger problem - we don't know how to use exceptions."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Is it necessary to add the suffix `on_head`, because it belongs to` bbox_head`?"
    },
    {
      "prediction": "I don't think this is the case, but it would be better to use `--with-modern-grub=no` instead of `--with-modern-grub=no` instead of `--with-modern-grub=no` instead of `--with-modern-grub=no` and `--with-modern-grub=no`",
      "reference": "Hmm, I wonder if this should just be e.g. `--with-grub-2.02` instead. (Not sure Autoconf supports periods in these switches.) Today's modern GRUB is tomorrow's ancient GRUB. :) Or maybe we should be specific about the feature this is enabling, which might be safer given that each distro carries so many patches. E.g. `--without-grub-efi-16-suffixes`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Add a GetSerialPortOutput method to Instance that way you don't need to access the client, also it makes the call cleaner as you don't have the odd i.Client and path.Base(i.Project), path.Base(i.Zone)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `/workshops/24-design-for-developers?utm_source=podcast` and `/workshops/19-design-for-developers?utm_source=5by5` and `/workshops/19-design-for-developers?utm_source=podcast`",
      "reference": "Line is too long. [104/80]"
    },
    {
      "prediction": "I think this is a bug in the clusterpool controller.",
      "reference": "Since CD updates (assignment & power state) are now done in this controller..."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Hmm I'd rather not support this option going forward - it seems like a one-off just to work around this particular issue. Would it be fine to just remove the `deepStackTrace` option? The rest of the PR looks great - I love the idea of switching to sets."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "on the one hand I like how little this is doing. On the other hand, `inbound_mail_parser` is doing most of the work here so maybe it's not as helpful as I originally thought"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This line is too long"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This isn't a fatal error, we don't want to crash just because we can't set configs, we have sane defaults set"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a better way to do this.",
      "reference": "I wondered why `buffer` was passed into `LookupPath`. What is happening here? Is `buffer[:0]` equivalent to `[]V4TrieEntry{}`, and hence `buffer` isn't needed any more?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the user_message_author.",
      "reference": "I don't really like the name of this file, especially the encoding of an implementation detail (the fact that it's a table) in the name. Can we just use `_message_body.html.erb` instead maybe?"
    },
    {
      "prediction": "I think this is a hack, but it would be better to use `json:\"action,omitempty\" protobuf:\"bytes,6,opt,name=action,casttype=github.com/vmware-tanzu/antrea/pkg/apis/security/v1alpha1.RuleAction` instead of `json:\"action,omitempty\" protobuf:\"bytes,6,opt,name=action,casttype=github.com/vmware-tanzu",
      "reference": "Feel better not to expose our internal implementation in API/CRD, so no need to mention agent here. Consider: EnableLogging indicates whether or not to generate logs when rules are matched. Default to false."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "use `NebulaKeyUtilsV3::dataVersionValue()` to replace the literal value?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "No need for the `\\` here, inside parentheses whitespace is ignored by Python."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This doesn't seem like the right expected result... it should be the same as the `clientCert` var defined above."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "need to rename this now."
    },
    {
      "prediction": "I think this should be ignored.",
      "reference": "NIT: This shouldn't be a TODO. It is just a note isn't it?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I changed this to an error, that seems more appropriate than a warning here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change could mute unit test failure, but it is better to update unit tests"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "All other places that access `notificationIdsInUse` are in methods with descriptive names. We should do the same here. Maybe `markNotificationIdAsFree()`?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "keep as `ErrNotFound`, it is the same convention as in other packages"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "Same here, we need to call `callback` in else branch"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "At this point we already check that the record is valid and so it could never be nulll"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Would it not be more sensible just to move setting of the title to later in the method rather than duplicating it here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "why not do it in `reclaimExpiredSessions`? and `pushSessionToCache` can delete"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `norm_cfg` and `norm_eval` and `norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg` and `norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm_cfg.norm",
      "reference": "out_channels/num_outs/type are unnecessary"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You can create an issue for it and put it on the backlog so we don't forget it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So now we are checking twice, both here and in `weaveCIDRsFromConfig`. Not great. I suggest changing the `ok` return of `weaveCIDRsFromConfig` to a messsage (or error?) instead, which we can then log."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "An alternative to setting format to the default in Package.__init__ would be to set it in create_package. I think we can assume all packages are created by create_package, but not necessarily by build_package."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Let's add fee recipient as well."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `FileDownloadTarget` class.",
      "reference": "No need for those with `super-init-not-called`, as pylint already only turns things off for this function and it's needed for the entire function."
    },
    {
      "prediction": "I don't think this is the default.",
      "reference": "I think there's another spot for this in DefaultCapabilityMatcher"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `currently_awaiting_steps.first`?",
      "reference": "this name seems pretty vague -- thoughts on a more descriptive method name?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the OpenTelemetry Authors.",
      "reference": "what changed in this line?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `select( CORE_SITE).getCurrentEntityURL()`.",
      "reference": "Instead of doing this let's add another function similar to `hasZeroData` for selecting the `reportArgs` since this is all sourced from selected values. Then `hasZeroData` can use this internally, as well as the component itself. Since this function would be internal just for the purpose of avoiding duplication, we don't need to expose it on the component the same way though."
    },
    {
      "prediction": "I'm not sure why this is the exception class name?",
      "reference": "This line was useful for auto-completion, I think it should be re-added with specifying the var name (`$exception`) and simplifying the FQCN."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This looks like you're not collecting everything from the error channel."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `checkout.plan.name` and `plan.user_email` and `plan.user_email`.",
      "reference": "This currently violates the Law of Demeter. Using `checkout.plan_name` is the quick resolution."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "is there any scenario when `$temporaryFilename` can be null?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "this is for the `boolean isRoot = root == rowType` check, which seems to be on purpose, but maybe you could double check whether using ref. equality here is still wanted? Same for `SparkTypeToType`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "No need to damage after `roots_drag_icon_update_position`, this is already done in `roots_drag_icon_update_position`"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `torch.device('cpu')` for the `torch.device('cpu')`.",
      "reference": "Have you tested exporting to ONNX with `device=cuda`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we also need to validate `envName` flag then? `appName` and `envName` are used in `initLogsSvc` which are called by `svc logs` from within `Execute()`"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "@LukeTowers I think I would prefer that we don't force it, on the basis that: a) some people would be opting to configure their web server to protect against this kind of attack and would disable this feature in October CMS to get a small performance increase. b) it might be a bit misleading to say that `app.trustedHosts` set to `false` disables the feature entirely, just to have it be overridden here regardless."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i like that you are trying to correct the naming, but its making the PR longer :( i guess in future we can do such changes in separate PRs"
    },
    {
      "prediction": "This is a label of ARIA Label",
      "reference": "Are we marking what the browser's accessibility tree says or what screen readers with those browsers say?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This method should behave as intended, to block until it reads an EOF from the other side."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I prefer starts with `Failed to xxx`, how about `Failed to perform health check on xxx`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "All these calls make me think we should refactor how traces are started and allow \"source tags\" that we initialize a trace with. I'd like to do this in a follow up."
    },
    {
      "prediction": "I'm not sure if this is a bug in the future.",
      "reference": "This file shouldn't be in this PR"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This now causes `LessSpecificReturnStatement - src/somefile.php:9:32 - The type 'non-empty-list<5|string>' is more general than the declared return type 'non-empty-list<string>' for takesList`, which seems correct to me. The type `non-empty-list<5|string>` contains the type `non-empty-list<string>`. Thoughts?"
    },
    {
      "prediction": "I think this should be a better way to do this. I don't think it's a better way to do this.",
      "reference": "Are you going to change that back?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "we have a standard format for putting these together elsewhere, it does the filter check first and errors out and then sets based on the value. i think this should be adjusted to do that. there's no logical change, just an approach change."
    },
    {
      "prediction": "I'm not sure if this is a wrapping counter.",
      "reference": "Note this should be `delay` instead of `scale` here. I'll fix this in my branch."
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "`on` likely still needs a bind, similar to `this.resetProgress = this.resetProgress.bind(this)` correct?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Considering the trade-off between training speed and accuracy, multi-scale training is temporarily kept. More elegant implementation will be adopted in the future."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Can you move this up along with the other builtin libraries?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I actually think it makes sense to reposition this checkbox after the notifyForPendingUpdateCheckBox. The current order of check boxes is a bit arbitrary now."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we have both `before` and `after`? Naively I would expect this to work as follows: `plz query changed` with no arguments compares the current working directory state to the last commit (i.e. HEAD, i.e. a noop when directly on a git commit). `plz query changed --since [reflike]` compare the current working directory state to the given reflike. So for CI I would expect to run something like `plz query changed --since @{upstream} (or origin/master I guess)`. And on merge I'd either run everything or just `plz query changed --since HEAD^` (given our workflow) - I don't think I'd ever want to do anything else. Either way I think before and after are slightly confusing terms here."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Is there a reason why we can't use `~dst`? It feels like that could be good enough.I would like to avoid extending the filter syntax unless there's an urgent need. :)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why local and not UTC?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "2012 is a retryable error. Will avoiding rgenerating it here cause a difference in behavior in createServer() ?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "move to line 14 below"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "the method name should match teh docs"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Won't this happen automatically when we flip the default version in the config?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This would also change back to /var/www/html/docroot if we go that way."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This still needs to use the new option. We'll need tests for it too."
    },
    {
      "prediction": "I think this is a bug in the GNU General Public License, but it's a bug in the GNU General Public License.",
      "reference": "We are no longer including file name in the source files."
    },
    {
      "prediction": "I don't think this is necessary.",
      "reference": "no need for this. Devise provides us with `current_user` and `user_signed_in?` helpers."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Would `Object.equals(capability.getName(), NAME)` would be safer, as you wouldn't have to do null checks?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `example_group.example` and `example_group.example_group.run`?",
      "reference": "Hmm, I wonder if we should revert #1862 instead? BTW, what failure do you get w/o this line?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "since there are several places where we do 1) get secret key ref and 2) validate URL, maybe it's worth having a common method? it could also trim spaces as done here (but not at the other places currently)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "TestNormalize... I would also split them"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "All changes to this file are going to conflict with #7599. Please revert these as well. They will be addressed during the Python 3 transition."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just thought, using spinlock (busy wait with compare and swap) that generates 2 random numbers inside rlock. We know that collisions are rare and we don't need that \"large\" write lock really but lock namely for \"rand\". Or least use a separate Lock (Mutex), namely for \"rand\" (wrap it into method). Mutex will use some sort of spinlock as well but it may use some linked list to make it more fair."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we grab it directly from `__pkginfo__` as that is the source of truth for the version?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We can revert this to reduce the diff of the PR."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This looks weird. `isCloud` should define if it is a cloud or no. Here it does it partially, and it can be overriden by protoPkg value (which also an argument to this function). Please make sure that isCloud completely defines the cloud thing. (i.e. it an be as straightforward as moving `protoPkg.contains(\"cloud\")` from here to the place where `assembleGoImportPath` is called."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Declaring fileflags to be of type LobTgtFileFlags would eliminate the need for all this casting. And would be safer. (Not a show-stopper though.)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change prevents a user understanding how their server is configured. Best to leave at `info` level."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Typically we would add something to the build system environment to differentiate this; also is there an alternative that can be used with older OpenSSL? Other folks who are committers will need to decide if it is worth supporting an older and likely quite vulnerable (to hacks) OpenSSL library."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "`readActiveBlockProducersByHeightTests` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Falls back on `Constants.ID` if there's no custom field set."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I believe this is what we want to rearrange: this in.skip() should not be happening here, in the open method, but in the setOffset() method itself. Because we want to be able to change that offset after the initial open. The setOffset() method will need to throw an IOException, if it's called while the InputStream is still null; or if the skip() call itself results in an IOException()"
    },
    {
      "prediction": "I'm not sure if this is a primitive type. I'm not sure if this is a primitive type.",
      "reference": "In case the method is `void`, there won't be any children and `getChild(0)` throws. We'll need to check with `isVoid()` for that case. I'll update this when I merge."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "If the yarpc.Interceptors wrapper will be added to any user interceptor, why not do it transitively. Can save one step for users. Same apply to filter."
    },
    {
      "prediction": "I'm not sure why this should be done here, but I'm not sure why this should be done here.",
      "reference": "Is there anything we should do in the event we're unable to renaming the directory?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "How is this env var populated? Can this be retrieved from cluster metadata?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should probably skip the success event here, since it could be a noop."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "I added this here because people cards (which depends on cardBuilder) had this added in blurhash. Not sure when this is used though cc @JustAMan"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Let's keep this line in the docstring, to let end users know they shouldn't be using this directly."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "can do the same for other validateXXX()"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this necessary?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please move this import upper to other similar imports"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Include the key word \"translated\". Otherwise the reader will find this confusing."
    },
    {
      "prediction": "I think this is a singleton, but it's not a singleton.",
      "reference": "why. is this called per request? if so this also adds a lock internally. can we not add this at the moment until analyzed as this assumption isnt carried to the several other impls. the only other consumer of this is the http api and that isnt hit often enough for specializations."
    },
    {
      "prediction": "I don't think this is the case for the first option, but it's not the case for the first option, but it's not the case for the first option.",
      "reference": "I believe this means dependent checks can no longer operate on virtual nodes, which is something we've been pushing for lately. We may need to find a different way to solve this issue, as I don't think we want to cause a regression while fixing a bug."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "ditto about use of `abspath`"
    },
    {
      "prediction": "I think this is the same as `isEvenlyDivisibleByAllNumbersFrom1To(max, val)`",
      "reference": "this reduces the runtime by 50 times"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Probably best not to have an empty test...."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "direct `newInstance` call is also deprecated now"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We have a bit of a convention where imports are split into three blocks: first Go standard library, then imports from outside the repo, then imports from inside the repo."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why was this change needed?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "can you use this opportunity to remove `.readlines()` useless list creation? (`addresses = [l for l in fd if l.find(\"netmask\") >= 0]`)"
    },
    {
      "prediction": "I think this is a hack, but it would be better to do it with `_output` and `status\": \"success\"` instead of `status: success` and `status\": \"success\"`.",
      "reference": "Why does this check differ from `plan_ssh.rb`?"
    },
    {
      "prediction": "I don't think this is a bug in go-fsm, but it's a bug in go-fsm, but it's a bug in go-fsm, but it's a bug in go-fsm.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "It was @lodejard who initially suggested this pattern. I think that it had something to do about prioritizing future writes even if there was a pending write operation ready to handle the newly requested write. I'm not sure I fully understood the explanation for having up to 3 pending write requests, because only having one queued write at a time still makes sense to me. I'll talk to him about it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We have cli --online_weight_clear in cli.cpp"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So the request.Headers is a map of []string. Are you sure that the HTTP library doesn't already do this split for us?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "How is this message used? Can we remove the \"crashed executor/container\" part which is an implementation detail?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Instead of building in routing for a browser-specific command, could you refactor the HttpCommandExecutor to allow arbitrary commands to be registered?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Space after `=`."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "if just need to do something after createInvocation just override and call super first is enough?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "By the way, I fixed `announce` method (missing `super` call to announce JDK version)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'm not sure about that... This line can produce <code>ClassCastException</code> if <code>Comparator</code> do not check this."
    },
    {
      "prediction": "I think this is a bug in MDOps.",
      "reference": "There wasn't any special reason for this to return a pointer, right?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Why the need for a `ConcurrentHashMap`?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `titleNaturalSort` option.",
      "reference": "New code should use strict equality `===`"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "`expect(resources['Notify[local pid]']['events'][0]['desired_value']).to match(/(\\d+)/)` seems clearer."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Removed now-unneeded param."
    },
    {
      "prediction": "This is a hack.",
      "reference": "(NON-blocking, this can be tracked in follow up issue) @anorth @mishmosh is the toplevel getting too crowded? Should we have a `network` grandparent command, or maybe a `stats` command?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The `_x` function needs to be imported at the top of the file (in addition to `__`)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This is functionally equivalent to the code it replaces."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "can you change the field name here to \"InterfaceAssociationProtocol\"? same for the Config struct in agent/ecscni/types.go. i think it's better to keep the field name consistent between agent and acs payload"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "See above, same for the other cases."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Shouldn't line 313 be public \\<T\\> SettableGauge\\<T\\> **settable**Gauge(String name) { ? It would also be good to call it a few times and with differnet types (Long, Integer, String) in the test as well."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I would prefer to just fix the occurences of this new check rather than disable them"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `feedDataHosted` property.",
      "reference": "The tests should be fixed in #4841, so this is no longer needed"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "I think it should been in `SharedKernel` module."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can we add some description for this field?  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should its name be Time or Duration? I can see them both."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this used anywhere?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I believe that you can use `assert` instead of `require` here and in the following lines"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "In `storagemarket.go` you used `nil` for an unwanted out parameter. Do something consistent (nil seems fine if supported)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "is this a new pattern we use in bee? interesting"
    },
    {
      "prediction": "I think this is a bug in qstack.",
      "reference": "If you think this PR works, i'll clean this up before resubmitting."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "are you sure you can read version by this artifactid?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We can get rid of this import then."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we do our own vtable?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `config.routes_app` and `config.routes_app.routes_app.routes_app.routes_app` and `config.routes_app.routes_app.routes_app.routes_app.routes_app.routes_app.routes_app.routes_app`",
      "reference": "This is the actual fix."
    },
    {
      "prediction": "I think this is the default sync interval.",
      "reference": "If sync has really a negative impact, this is just moving the issue from 10sec to 60sec. Wonder if you should not expose the (auto)sync params so users can decide."
    },
    {
      "prediction": "I think this should be called when MapLen returns true. It should be called when MapLen returns true.",
      "reference": "should be called => will be called"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "not sure whether we should do this. It may cause problem that delegates upgrade their nodes at different time, that they will have different \"last block time\", some use \"commit time\", some use \"block time\". Potential solution: Only use block time after berling, and then delete it in the next version after berling. Open to discussion."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "So one question I have is why is the error coming back from `buildReplicaPositions` not an `Assign.AssignmentException`? Is it because it is wrapped in a `SolrException` from the remote node?"
    },
    {
      "prediction": "I think this is a bug in pytest.raises(TypeError):",
      "reference": "`dt` won't work for some reason?"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is this because \"KOALAS_USAGE_LOGGER\" can be `None` ??"
    },
    {
      "prediction": "This is not a good idea, but it's not a good idea.",
      "reference": "I like it but maybe the better name will be EthGasPriceConstants or EthGasPriceEstimatorConstants? but Constants not Config"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I would inline the constructor as well"
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "I'm not confident about this..."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "There is also `v1alpha1.CertificateRequestKind` I think?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we rename it to make it less confusing? Instead of \"sender-gcpbroker\", maybe name it to \"retryable-sender\""
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "So looking at the definition of the `literal()` function in this class, it seems it's possible for it to return null. I guess it's not a concern as we would get NPE on the above call at line 136 when trying to call `.to` if `literal()` returned `null` before even getting to this part that calls `literal().value()`, but something I thought I'd bring up. Perhaps something we might follow up on in another issue or possibly I just missed the workflow that makes `literal()`'s result non-null by the time this `bindLiteralOperration` is called."
    },
    {
      "prediction": "I don't think this should be a test case, but it's not a test case.",
      "reference": "Why did you break the line? It looks like it is under 80 characters without the break and it is inside parens so no need for backslash anyway"
    },
    {
      "prediction": "I don't think this is a bug in sklearn.base.BaseEstimator. This is a bug in sklearn.base.BaseEstimator. This is a bug in sklearn.base.BaseEstimator. This is a bug in sklearn.base.BaseEstimator. This is a bug in sklearn.base.BaseEstimator. This is a bug in sklearn.base.BaseEstimator.",
      "reference": "@guolinke Don't you mind to rename this variable to `DATATABLE_INSTALLED`, for the consistency with other variables (for example, there are `PANDAS_INSTALLED` but not `PD_INSTALLED`). Also, `DT` is a little bit confusing: sometimes `dt` is used for `datetime`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `slowest_examples.each` method.",
      "reference": "We're fine with double quotes here. Just for future reference."
    },
    {
      "prediction": "I think this is a bug in yarpcerrors.CodeOK.",
      "reference": "can we keep this around? We should make sure we can distinguish between properly wrapped errors and \"unwrapped\" errors"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`RecordPipelineShaderStage()` might change `topology_at_rasterizer `, according to shader code, so we should check `pInputAssemblyState `first."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should we just inline the assets here? I can't think of an advantage to having them in a separate file."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "detectStaleEndpoints to be more specific?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Please create a new issue for addressing this (if there isn't one already), so it doesn't get lost."
    },
    {
      "prediction": "I don't think this is a bit of a hack.",
      "reference": "Nothing was ever coming out of this channel because its already being consumed. Create a new channel here and feed it in HandleNewHead method."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is deliberately at this level."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "payload entered on command line is in hex-encoded format should use same processing as in ioctl/cmd/action/actiontransfer.go"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "should this be kept in the `else` branch?"
    },
    {
      "prediction": "I don't think this is a good idea to use `sync` instead of `sync` instead of `sync` instead of `sync`",
      "reference": "Why not put this below \"strings\"?"
    },
    {
      "prediction": "I don't think this should be used in the future.",
      "reference": "Make it `internal` if it's just for testing."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "What is triggering this message in this file?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Are you sure this should be removed?"
    },
    {
      "prediction": "I'm not sure why this is a proxy settings object, but it's not a proxy settings object.",
      "reference": "What's that good for? The field is initialized in the constructor."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This shouldn't be necessary (same below). Do you have a traceback for me?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it would be better to do it with the same name. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "No newline needed here."
    },
    {
      "prediction": "I don't know how to import this package?",
      "reference": "Why a separate block?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Probably better to ask @AssadHashmi or another AArch64 expert for a review rather than me -- @AssadHashmi if you could confirm that these status registers are 64-bit despite having only a few fields?"
    },
    {
      "prediction": "I don't think it's a bit of a hack, but it's a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "`purpose` and `coin_type` and `account` would mimic the BIP-0044 wording, but it's up to you."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is this the critical change? It does seem wrong to use Select() instead of Checked = true. Not sure why that would pass sometimes and not others, though."
    },
    {
      "prediction": "I don't think this is a good idea to do with the `hivev1.MachinePool` and `hivev1.OSDisk` parameters.",
      "reference": "Seems a little low, but is this an installer default?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Maybe we could provide our own `configure` function that includes `logger._logger = None` because I don't see a use case in kinto for using `reset_logger` besides configuring the logger."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This will cause the same breakage that was caused when we added Proof to Block. Be sure to let people (infra?) know ahead of time"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Fixed the test; @strib want to validate that this is okay? Seems to be consistent new GC behavior."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Afaict, nothing cares"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I must be missing something, but why does not having a node cache imply not neededing to re-embed the block changes, in particular? Isn't it just the fact that we don't do any writes?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are these changes from `class` to `struct` breaking if called from an older version of `Datadog.Trace.ClrProfiler.Managed`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "These are just aliases now"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Does this mean we can remove `raw` from `_head_contents` partial?"
    },
    {
      "prediction": "I think this should be `this.splashWindow.close();` and `this.splashWindow.close();` and `this.splashWindow.close();` and `this.splashWindow.close();` and `this.splashWindow.close();` and `this.splashWindow.close();`",
      "reference": "`isDestroyed` is a function, not a property. This condition will always return false."
    },
    {
      "prediction": "I don't think it's a bug in this case, but it's a bug in the future.",
      "reference": "Why are we adding these versions?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "fyi, you can do this by doing `.info(\"string %s %s\", formatparam, formatparam2)` instead of doing a string format with `\"str\" % (params)` the idea is that it'll only do the string interpolation if logging is enabled for this level, which theoretically is an optimisation, but in this case probably isn't important"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it's not the right thing to do.",
      "reference": "Would this work, as a one liner? `setTimeout(window.location.reload, 5000);`"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Can you move `crypto/tls` into the block at the top with all the other stdlib imports?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "What is the motivation for this change?"
    },
    {
      "prediction": "I think this method should not retry.",
      "reference": "OK, so the concrete implementation will loop? But then it's important that this method waits for a while before it returns no messages. To be specific, a GCP implementation that set `ReturnImmediately` to true or false would both satisfy this requirement, but the first would cause busy-waiting."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The data structure of `MatchClauseContext` may need to be redesigned."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You say on the issue that something has to be receiving while the messages are being published. But here it's possible that the publish goroutine starts, and maybe even completes, before Receive is ever called."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "how do we know that the step in question is an approval type step?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "JMX offers normal APIs for this. I don't think you want the glassfish one."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Is this still Java 8 compatible? @danieldietrich do we need a separate, modularized Java 9 release also?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Should update the user input address and filter modes and pass those in fillSamplerDescriptor ?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "This object should be in `lib/music/show.rb` and you should also wrap this object in the `Faker::Music::Show`."
    },
    {
      "prediction": "I think this is a bug in Puppet.",
      "reference": "I think logic will have to move to bolt since the vague discussions around bolt run plan --noop is that it would just skip any tasks that don't support_noop rather than error. This is fine until we actually elaborate that though."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "File is not `goimports`-ed"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why should unknown raise a 403?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The true clause of your condition, can't this just be c._nextState since `assign({}, c._nextState)` is equal to returning c._nextState, or am I misunderstanding something here?"
    },
    {
      "prediction": "I don't think this is the default value for maxResult.",
      "reference": "nit: align the leftmost quotes"
    },
    {
      "prediction": "I think this is the default value for the `clusterPort` field.",
      "reference": "Probably \"server port\" -> \"TCP port\""
    },
    {
      "prediction": "I'm not sure if this is a `Lucene80Codec` class.",
      "reference": "can you use FilterCodec instead?"
    },
    {
      "prediction": "I think this is the default value, but it's not the default value, but it's the default value.",
      "reference": "I know there's only two values but I find it a bit confusing that it's true/false. Could you change it to a string enum with values \"portrait\" and \"landscape\"? Then when calling printToPdf you can just do `landscape: Setting.value('export.pdfPageOrientation') === 'landscape'`"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I think this migration should fail for MDBX if it uses old table names"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should this be negated? `!@options[:hosts_file].nil?` Otherwise it'll enter the `if` statement and `nil` will be passed to `HostsFileParser.parse_hosts_file`, which I'm assuming is bad."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `applyOnReload` parameter.",
      "reference": "I'm doubting if adding a bool here is a good idea. Maybe it should be an option object? Otherwise it's hard to extend. But an option object is a bit strange in a fluent API? What do you think @snakefoot ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is used in o.a.l.sandbox.search.PhraseWildcardQuery."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "view should be loaded on start for both statedb and factory"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why rename? Just curious..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is this needed? I think it calls the super function that already does that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This might slow down the inference time, are we sure we need to do that?"
    },
    {
      "prediction": "I don't think this is a good idea to use `gocloud.dev/howto/sql/#aws` here.",
      "reference": "This would read better if you add \"Skip code/lines\" or (exclude/hide code if you follow my earlier suggestion\")"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Looks like glassfish went a bit nuts doing a refactor"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `ForceFlushAsync` method, but I'm not sure if this is the right thing to do with the `ForceFlushAsync` method, but I'm not sure if this is the right thing to do with the `ForceFlushAsync` method, but I'm not sure if this is the right thing to do with the `ForceFlushAsync` method.",
      "reference": "nit: allocate the list using the number of processors."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Was this change triggered by baseline?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This code was doing nothing as far as I can tell and was making the SQL find nothing with the new version of Rails. Remove it unless someone can explain why it is there."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Setting browser based login as the default for `RestAPIExplorer`."
    },
    {
      "prediction": "I don't think this is the best split.",
      "reference": "maybe we can do this in Init function?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How about if request ID not set, service should generate a random uuid?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "minor: this is an opportunity for you to split these long lines into multiple lines :)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `url` parameter.",
      "reference": "It would be nice to have exception dumped somewhere (debug logs, info logs)."
    },
    {
      "prediction": "I think this is a hack, but I think it's a bug in go-cloud.",
      "reference": "So I don't think this is right, as discussed on #657."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "should the group_id = \"{0}\" be group_id = %s You'd still keep the {} for the group_members_{} for the tablename but make the filter clause parameterized."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Path can contain variable pattern in the middle. Also, `$` is not enough to tell if this is JMeter variable. We have correct variable detecting somewhere in our code."
    },
    {
      "prediction": "I'm not sure if this is a static method.",
      "reference": "@bennothommo can you revert this section? It shouldn't be required."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Minor: maybe move the above to a `#fiscal_year` method?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You should use the current directory instead - it's a temporary directory that will get removed when the test is done."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we don't need synchronization here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think this should be changed since on the reactive side we don't support anonymous users."
    },
    {
      "prediction": "I think this is a bug in Mongoid.",
      "reference": "Maybe this `if` should be on line 118?"
    },
    {
      "prediction": "I'm not sure why this is the case for the `less than equal bucket count`?",
      "reference": "Cool. (I thought I had fixed this already in #812.)"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "I intend to do this as soon as I have tests passing."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please remove the `test_*` from the filename - otherwise pytest will try to collect tests from it."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Did you file a bug to follow up on this?"
    },
    {
      "prediction": "I don't think this is the default value for the `vectorization-enabled` property.",
      "reference": "Looks like these 4 lines didn't actually change. Can you revert the whitespace changes here?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This can't be merged with any usage of `require 'pathname'` in lib, it's not always available and we don't want false positives for people (where they don't realise they needed to requite it). Its also unnecessary, no other formatter uses it to look up failure locations. See the exception presenter etc for how we format lines."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It would be nice to fix the indentation above."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do with it.",
      "reference": "`short_names` is still optional, so `=` that indicates it has to stay there."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "missing calling of this method"
    },
    {
      "prediction": "I don't think this is the right thing to do with this.",
      "reference": "We could get rid of this dependency being forced on clients by changing the `StackConfiguration` interface abstraction to deal with strings instead of `cloudformation.Parameters` and `cloudformation.Tags`, and internally to the `cloudformation` package translate the input strings into the `service/cloudformation` package specific values hiding that from consumers. I don't think that should be taken on as part of this PR, but I think we should consider doing it at some point."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `kubebuilder:printcolumn:name=\"action\",type=string,JSONPath=`.spec.action` and `kubebuilder:printcolumn:name=\"duration\",type=string,JSONPath=`.spec.duration` and `kubebuilder:printcolumn:name=\"duration\",type=string,JSONPath=`.spec.duration` and `kubebuilder:printcolumn:name",
      "reference": "`StressChaos` does not contains a field .spec.action"
    },
    {
      "prediction": "I'm not sure why this is a function call?",
      "reference": "Non-int literal strings are no longer coercible to int, I think this is an improvement. Without this change it now reports `InvalidArgument`."
    },
    {
      "prediction": "I don't know how to use `Array.isArray(a[0])`?",
      "reference": "I this used anyplace?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why was this change required?"
    },
    {
      "prediction": "I don't think this is a public API package.",
      "reference": "I like that we have this attribute here. However, I think the way we use it right now might be confusing in the future. For example, when only camunda admin is checked, this exception will be instantiated with a message and `missingAdminRole` is `false`. I think that is counter-intuitive. I would expect this exception to have `missingAdminRole` set to `true`. With this explicit information, the exception message could now be generated inside this exception class with the text block that is currently used in the authorization manager. We could maybe generally reuse that text block then also for the case where a user is no admin and also has none of the required permissions. I haven't tried it myself but I think it would be great if we could streamline those things a bit more if we're working on it now. Let me know what you think.  "
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack.",
      "reference": "Not sure why we're creating a new `ByteBuffer` here, ideally this refers to the existing one?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the user and site.",
      "reference": "Same here re: `STORE_NAME` to `MODULES_SEARCH_CONSOLE`."
    },
    {
      "prediction": "I don't think this should be the case.",
      "reference": "I could've sworn I got a `403` myself when I got that response locally. Is `200` what the API would send back for a `permission: false` tag?"
    },
    {
      "prediction": "I don't think this is a bit of a hack, but I don't think it's a bit of a hack.",
      "reference": "This attribute was intentionally private. - lets force usage of factory `NewIdentityManager()` - lets ramake to `NewIdentityManager(keydir string)` -> `NewIdentityManager(keystore keystoreManager)`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is this too frequent?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "will this not make it possible to use a zip file, e.g. on other importers who do not have to support it ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Needs to be mentioned in `__all__` below."
    },
    {
      "prediction": "I think this is a bug in signalfd_thread_exit.",
      "reference": "What if the app's signal handler, executed at pre-syscall for epoll_pwait, executes its own epoll_pwait? For that matter: what happens natively if that happens? I would not expect the kernel to keep a stack -- does that clobber the kernel's stored pre-syscall mask?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Nit: missing a space. I think we should phrase the new content a little differently. \"It is important\" isn't very clear. I think it should be \"offsets will be returned in sorted order.\""
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can you remove this blank line and put the added import in sorted order (likely your editor will do this)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Even if `pthread_create()` for `ocsp_updater_thread()` fails, `h2o` can continue to serve. But I'm a little worried whether `h2o` should continue to serve in this case. How about you?"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I'm not sure if this is the case.",
      "reference": "I like introduction of these constants for account/container creation, but the `ACCOUNT_CHOOSE` one isn't needed I think. This should instead be an \"empty\" value (either `''` or `0`), to indicate more clearly that this field is not filled. It should be the same for choosing a container."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "I noticed that passing in `[]` for the locales argument instead of 'undefined' seems to have the same effect. I think that's preferred over passing in `undefined` as a value, and unfortunately passing in `null` seems to throw an error."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "1. `0` is redundant. 2. We should save result of `strings.LastIndex(DbCfg.Host, \":\")` to a variable and reuse."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you envision \"new\" servers not supporting header, or is it more a way to test mix of old and new? If so, we could make it a \"private\" (non exported) option."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For future reference. Try not to do refactoring in the same PR which solves some bug or implements some feature. Not to clutter reading. Do it in separate PR."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure about changing the flag name. unit is more accurate, but for I think for most people asset is also a fine name to use."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `GetConsoleWindow` and `ShowWindow` functions.",
      "reference": "Which windows gets activated? A random other window?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Just to make sure, this is totally lossless? If I put a v2 there, then it gets upgraded to v3, but my function expects v2, then this is fine and nothing is lost?"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "In the past, we have 3 Flink streaming jobs (1 for each AWS region) writing to the same table. We need to write to 3 different watermark table properties (1 for each region). Watermark consumer then use the min value to determine the overall table watermark. A provider pattern similar to `WRITE_LOCATION_PROVIDER_IMPL` can work. A default impl could be a single property name. not sure if there is a simpler way to achieve this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you change this to `ResolvedUsersMap` and build a new map with both readers/writers? That way, we get the nice side effect of not exposing the internal map of the handle, and simplifying the callers a bit."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `mongodb.options.cryptdConnectionString`?",
      "reference": "I typically try to avoid nested ternary expressions. Can we rewrite this as if statements? Worst case, can we break it out into its own function?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do we still support handshakes without SNI present?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Maybe it's because I work too much on a centralized logging system but it could be great to add a \"category\" like \"attribute\", \"substitution\", \"include directive\", \"macro\", \"extension\"..."
    },
    {
      "prediction": "This is a hack.",
      "reference": "it have no sense in python -> it makes no sense in python"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "maybe just do a separate implementation of the pool for openvpn case? It's a bit confusing having two methods here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "how is it possible to have a `topology` that is falsey when we had to call `topology.connect` in order to get here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Do we need this expectation? If we don't call this method on `PlanFinder` there's no way for the `10` to be returned. Seems somewhat redundant. What do you think?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We need to do the same for edgecore"
    },
    {
      "prediction": "I think this should be a mock handler, but it's not a mock handler, but it's not a mock handler, but it's not a mock handler.",
      "reference": "This fix has nothing to do with the product change. Just a fix I am making for the test issue."
    },
    {
      "prediction": "I think this should be a BatchingActivityProcessor.",
      "reference": "Don't know what should be the default. Lets keep BatchingProcessor for now. And revisit the area after beta."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with RSpec::Support.require_rspec_support?",
      "reference": "Ah that's how it's happening, it's probably using the `require_relative` in the optimised one and that counts as a different require to the bare one."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What happens if there is no NIB/XIB with that name?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "this is not necessary?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "typo: `asmsecrets \"github...`"
    },
    {
      "prediction": "I'm not sure if it's a string, but it's not a string, but it's not a string.",
      "reference": "I think that the JSON encoding should be handled by the control itself, not the sanitization function. This should only confirm that the input is correct, not reformat it  "
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Should we put a TODO here to route the http.Transport through here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Sorry, could you explain more about the issue? Doesn't ComputerName already default to local computer? > -ComputerName Specifies one or more Hyper-V hosts on which the virtual switch is to be configured. NetBIOS names, IP addresses, and fully qualified domain names are allowable. The default is the local computer. Use localhost or a dot (.) to specify the local computer explicitly."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "`allowError` is a big vague. Does this mean the test case is asserting that an error should occur? If it means \"maybe an error can occur, and that's okay\" -- what's an example of this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "return statements should not be cuddled if block has more than two lines (from `wsl`)"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Why does VirtualMachineMetrics have to implement Metric?"
    },
    {
      "prediction": "I think this should be the same as the one in the account manager.",
      "reference": "line is 121 characters"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "How's that linked esbench looking with slice?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "The split and join was probably done to ensure that this still works on Windows because os.path.dirname works differently depending on the os you're running under :(. It would probably be a little better to do `dirname, _, fn = path.rpartition('/')` if you want something cleaner than the split/join."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is not the right approach. The `Distributor` maintains a model of the current state of the Grid. That model already contains the information about every active session. We don't need to modify `SessionMap` to expose it further."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you make this a member var as all the other deadlines? Then you can drop the param to resetTimer() and simplify some of the code below iiuc."
    },
    {
      "prediction": "I think this should be the same as `MolToSmiles(itm.first)`?",
      "reference": "I don't understand the reason for the changes from unique_ptr to ROMOL_SPTR that you made in this file. The pointers aren't being shared or used elsewhere so I don't think there's any reason to make them shared. Did I miss something?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why change the variable name at all?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Since I'm still trying to keep these straight in my head, can you elaborate on what problem this solves?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the account report spam?",
      "reference": "Prefer TextUtils.isEmpty() which handles getReportSpamRecipient() being null"
    },
    {
      "prediction": "I don't think this is a bug in Selenium.",
      "reference": "Couldn't you just write this as an if/else or a guard clause like on line 87? Just seems a bit weird doing this conditional assignment for essentially an if/else."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Do we actually use Include anywhere yet or is this just for completion?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It still bugs me this was misspelled in the standard and now the wrong spelling is the commonly used one :wink:"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "seems we missed de-uglifying this one"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "i guess these types & cron / retry specific belong to a dedicated util / struct"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the right thing to do with the `sendKeys()` method.",
      "reference": "Also update line 2205 below"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "`direction` is referenced nowhere. Do I miss something?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `ember-cli-mirage`",
      "reference": "The two places this was used have been removed so we can fully remove this dependency."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is a duplicate generation of the same file as below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We may deprecate `gpus` if `gpu_ids` is specified."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Right now this is experimental and deeply flaky. We left this at `info` to make debugging user reports a lot easier."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "unnecessary spaces here are doubling the size of this otherwise extremely useful addition"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think we should use `FileExistsPolicy.Overwrite` instead. Files _should_ always be newer, but in the unlikely case they wouldn't be, I'm afraid some files would be overwritten and other not, leading to inconsistencies that will be hard to figure out."
    },
    {
      "prediction": "I think this is a bug in MolDraw2DSVG.",
      "reference": "this should probably be removed"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: I would actually prefer that pretty JSON is the default, with a flag for compressed JSON. Can we acheive that easily?"
    },
    {
      "prediction": "I don't think this is required.",
      "reference": "Will need to think about this one. `additionalIngressRules` feels a bit opaque in terms of eventual outcome."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Can we avoid making this public with the other updates?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Why did you change this equal instead of less or equal?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "missing final for the blockHash field"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `factory_girl_rails` or `factory_bot_rails`?",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`x_float` instead of `float_x`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `swiper/swiper-bundle.esm` or `swiper/swiper-bundle.css`?",
      "reference": "Is this for `No Babel config ...` from ESLint? If so, it will be fixed in my ES6 PR."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not important, but the code used to keep checking other cases even after one of them failed, and now it's not. Fine either way for me, just noticing."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "I think I saw this line in last PR, you can update your base branch and rebase to avoid this. And it would be awesome if you can rebase instead of merge each time you push PR to the `moby` branch, that will make the commits history clearer."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If this can change the PC of this thread, it requires handling: we can't blindly execute the syscall and lose control of the thread when the flags include CONTEXT_CONTROL. (Note that most docs imply that setting your own context this way is not supported or has undefined or unpredictable results: any idea how often that's the case, or does it generally work?) We need to handle in a similar fashion to NtContinue or setting another thread's context to ensure we retain control."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "@huzaifaiftikhar Changed the endpoint as suggested by Stephane in the latest commit."
    },
    {
      "prediction": "I think this is a bug in segmentio/stats.",
      "reference": "There's no core.Number yet. ;)"
    },
    {
      "prediction": "I don't think this is a problem with the `--volname <vol> --snapname <snap>`.",
      "reference": "..., ...will be posted."
    },
    {
      "prediction": "I think this is a bug in go-filecoin.",
      "reference": "Can you update this function to be `ShowHeader`? There is only one use of it at the moment in `tools/fast/series/get_head_block_height.go`."
    },
    {
      "prediction": "I don't think this is the default value for the package name.",
      "reference": "@akarve, this disables `tqdm` by default, is it intended? Also name `QUILT_USE_TQDM` might be too specific, IMHO `QUILT_INTERACTIVE` or `QUILT_PROGRESS_BARS` or something might be better."
    },
    {
      "prediction": "I think this should be the same thing as `addENIAttachmentToState` but it's not the same thing as `addENIAttachmentToState` and `addENIAttachmentToState` should be the same thing as `addENIAttachmentToState` and `addENIAttachmentToState` and `addENIAttachmentToState` should be the same thing as `addENIAttachmentToState` and `addENIAttachmentToState`",
      "reference": "unrelated but just changing for consistency with code below it"
    },
    {
      "prediction": "I think this should be a `shouldComponentUpdate` function. I think this should be a `shouldComponentUpdate` function.",
      "reference": "This will call `componentWillUpdate()` for mounts because the else clause is removed. It should only be called for updates."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We should add write inheritance too."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Please rename this to `LAMBDA_JAVA_OPTS`, and add a short description to the README."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should be in the same import group."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Operator precedence is very confusing here. Care to add parentheses? ` ((version or 0x0303) >= 0x0200)` Same below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "javaparser-core has no dependencies and it should stay that way. So no log4j. And even then there would have been a preference for slf4j."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Why not just retest all? it's not expensive (I think)."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "ecr and ecr0 aren't deterministically named here. This change will just cause confusion in the git history. Could you either: a) fix this and make it deterministic b) regenerate the mock until it doesn't flip definitions for ecr and ecr0"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `lsb_release -ds` command.",
      "reference": "This looks like bash... does this work in ruby? Or is the idea to inject the entire script into the subsequent commands?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't understand why this change is in this PR?"
    },
    {
      "prediction": "I think this is a bug in Blacklight.",
      "reference": "It's a little hard to tell from the diff, but as a result of this PR, the only non-deprecated helpers are: - `has_facet_values?` (probably not long for this world) - `render_facet_partials` (perhaps part of a future component) - `render_facet_limit` (possibly obsolete once components get traction) - `facet_field_in_params` (a little tricky to deprecate at the moment) - `facet_field_presenter`"
    },
    {
      "prediction": "I don't think this is a real object, but it's not a real object.",
      "reference": "The right-hand part shouldn't use `__proto__`. Should be just `PersonObject.__proto__ = Realm.Object`."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "the == case might be legit, or not? If there is no task written since last read, but we trigger a new read, would the min == max? Or should the upper layer handle that case?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Good catch! But is it guaranteed that `old_size < new_size` here? If not, wouldn't we want to take `min(old_size, new_size)` as the copy length?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "This is the only one that worries me a bit. It would be good if Brendan signed off on it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`LongRunningOperationDetailView` already has `isEmptyOperation`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This will always add the authorization header to the request object. Is this the right scope for these two lines? If username/password are not defined, it will encode 'Basic :'"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `updated_at_desc` operator?",
      "reference": "Don't think a scope adds much value for us here. Also, for future reference, you don't need to use the `self.all` it is implied. Could just be: `scope :updated_at_desc, -> { order(updated_at: :desc) }` No need to change this one now though, it works."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe `Base.` is unnecessary in this case, as the class already extends `Base`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Couldn't this result in images being scaled too small when the width is less than the height assuming the width is still what is being passed here?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `express.version.info` in the `express.version.info` module.",
      "reference": "Here also, let's not cache value on top of file, but use `plugins.getConfig(\"api\").offline_mode` directly where it is needed"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "You can combine the two checks into a single `!empty()` check."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Should we add a warning for anything over say 8M? Just suggesting that is not recommended?"
    },
    {
      "prediction": "I don't think this is a bit of a hack.",
      "reference": "Looks like there are no callers left of this function."
    },
    {
      "prediction": "I think this should be a context.DeadlineExceeded error, but it's not a context.DeadlineExceeded error.",
      "reference": "Should there still be a ` bool` trailing `showOutput`?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Did we can change to v1"
    },
    {
      "prediction": "I don't think this is a problem with the `_ancestorComponent` property, but it's not necessary for the `_ancestorComponent` property.",
      "reference": "Can you please double check that this won't break anything?"
    },
    {
      "prediction": "I think this is a bug in Nethermind.",
      "reference": "optionals, shouldn't need to be stated explicitly"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the gquic version range.",
      "reference": "That seems quite low - why not just 0x5130ffff?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Why is this needed ?"
    },
    {
      "prediction": "I don't think this is the case for the first_runs_free variable.",
      "reference": "`Bolt::Config.user_path` returns `nil` if there's no homedir, so this will still error in that case."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "nit: use %s for strings and %v for objects."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Same as before, the properties already exists in parent"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This fix is not quite correct. The `%s` should be replaced with `version` and the `%d` on line 39 should be replaced with `datetime.datetime.now().year`."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Maybe we should only set active = false if `strcmp(type, \"pause\") == 0`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `page_ranges` option.",
      "reference": "Same here. and all others."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Intentionally committed? I'm not against it, we already have a way to get goroutines without killing the process: `/keybase/.kbfs_profiles/goroutine`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I think this blank line may be removed"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `toggle=False` argument.",
      "reference": "I think this should be a keyword-only argument, i.e. do `def add(self, url, title, *, toggle=False):` and adjust the caller to do `toggle=toggle`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "@aimanrosli23 Judging from the commit description, I do not know why this file got changed so much. Could you help to double confirm if you do not revert the changes brought by commits: SHA-1: 643623147a1feaddd734ddd84604e1d8e9dcebee * MdeModulePkg/SdMmcPciHcDxe: Send SEND_STATUS at lower frequency SHA-1: 49accdedf956f175041040e677163b7cbb746283 * MdeModulePkg/SdMmcPciHcDxe: Hook SwitchClockFreq after SD clock start"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "How about YAML.load_file()"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe make this `volatile` or atomic as this can be set/read from different threads? Also, separately you may want to check if some of the methods here need to be `synchronized`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Check the return value of the drmgr ones."
    },
    {
      "prediction": "I'm not sure if this is a file upload, but it's not a file upload. I'm not sure if this is a file upload. I'm not sure if this is a file upload. I'm not sure if this is a file upload. I'm not sure if this is a file upload. I'm not sure if this is a file upload. I'm not sure if it's a file upload. I'm not a file upload. I'm not sure if it is.",
      "reference": "This should be `'cache'`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The name \"old\" might cause confusion here. After installation, the \"old\" repo is at an archived path, and the new migrated repo is at the old path. Maybe something like \"target\" or \"canonical\"?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is a collection.",
      "reference": "I think this is somewhat definitive proof that this error exists in `core` rather than `native`. We are correctly resolving the `readPreference` in the previous line, but you are able to identify that eventually the command generated in `core` is not decorated with the passed `readPreference`. Did you try to solve this there already?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "During genesis sync it can unwind 5M blocks?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "was it caused by the removal of removeTaskQueueManager() from this test?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `item_page_entry_info` method.",
      "reference": "Wouldn't it just be easier to force search_session to return `with_indifferent_access`? Since you've done the hard work already, I don't think there's a problem doing it this way, but.."
    },
    {
      "prediction": "I don't think this is the case where we need to check for the deadline.",
      "reference": "So, such tasks that could possibly not meet the deadline will never have a chance to run? I think this is not nice behavior, especially for those projects who has sometimes some very small tasks after the big one."
    },
    {
      "prediction": "I don't think this is a bug in the LuaScriptInterface::luaItemTypeCreate function.",
      "reference": "You should add the check above this line instead. If string is empty, don't even call the function."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "If clientCert attribute doesn't exist for some reason I set it to false."
    },
    {
      "prediction": "I think this is a bug in Travis CI.",
      "reference": "Do we need `app_host_flags` variable? We can directly concat with `flags`. `sh.cmd curl_cmd(unless Travis::Build.config&.ssl&.verify ? flags + ' -k' : flags, location, static_file_location), cmd_opts` right?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Walk should actually be completed (`onWalkCompleted`) after the event is stopped.   This also makes it possible for monster to walk by smaller paths."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "typo in `weather` (should be `whether`)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Thoughts on having the URI as the param, instead of a boolean? The default value would be the normal prod image, and then your test would override with the staging image."
    },
    {
      "prediction": "I don't think it's a bit of a hack.",
      "reference": "I'm surprised this is needed, but we should probably assert num_scan == 1 at least, otherwise I expect the file is pretty broken."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we set a default value for `partitions` and `{0, network::NetworkUtils::getAvailablePort()}` ?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Needs xml docs. The API names alone don't provide enough explanation about what these mean and how to set them. Also, we should provide some validation of inputs, such as MaxTime must be > MinTime, MinimumRate must be >= 0, etc. Consider making the properties readonly and adding a constructor that does these validations."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would it make sense to create an empty file here, perhaps in a tmp dir, instead of checking empty files into Git?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "This change is due to `clang_format` and is not related to this PR."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why did you not add the signals to the call of block_all_signals_except() and instead baked them into the function? Ok, if you had a good reason for it, otherwise I would add it to the except list of the function call, since that's what it was meant for."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if it's in the downloads list.",
      "reference": "Could this be done by mocking objects instead? I feel like this is changing too much of the actual logic just for the tests."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why not just use `ManifestContent` instead of `Integer`?"
    },
    {
      "prediction": "I think this should be a problem?",
      "reference": "can we do that in TxValidator?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "We definitely want some detailed and thoughtful docs being added to this type."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We would like this code to run, even when `config.XDPEnabled` is false, so that Felix can clean up its own XDP state after a restart."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "If the status is `ERR_SPACE_NOT_FOUND` why return `SUCCEEDED` ?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "It is is more appropriate to use `downsample_first`. If `downsample_first=True`, the downsample block is the first block and it is used for ResNet. If `downsample_first=False`, the downsample block is the last block, which is used by Hourglass network."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Would you mind removing the default parameter above? (I doubt I'll ever use defaults again since you still have to protect against callers explicitly passing `null` or `undefined`)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I don't know if there are strict conventions about this, but I think the name of the warning should be the diagnosis, not the suggested course of action. In this case, that would mean changing the name of the warning to `interactive-exit` or something like that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If `crt.Spec.CommonName` is not set, and `cert.Subject.CommonName` *is* set, we are not correctly handling it here."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the test.",
      "reference": "This isn't a test, so it shouldn't be named `test_init`. You could name it `cmdhistory_init` or so."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `pickle-protocol` option.",
      "reference": "why is this pulling from `self.spark_version` config section rather than the `spark` config section (`py-packages` appears to pull from a config section called `spark`)"
    },
    {
      "prediction": "I think this should be a bug in the tests.",
      "reference": "nit: Think it can be one line.."
    },
    {
      "prediction": "I'm not sure if this is needed?",
      "reference": "please inline imports"
    },
    {
      "prediction": "I don't think this is the case for a rootless container.",
      "reference": "This check is still correct in some cases, but I guess erroring out is acceptable if someone explicitly asked for an impossible cgroup configuration (now that we could in principle nest things). I would like to see a test for this though."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "Should we update integral to operate on a single column as well?"
    },
    {
      "prediction": "I don't think we need to use `cudaMemcpyAsync` instead of `cudaMemcpyAsync`.",
      "reference": "Doesn't belong to this PR"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Just for my own understanding, does aws ecs API take this token as a new input attribute? Which version of the aws sdk? I did not find it in the official aws sdk doc."
    },
    {
      "prediction": "I don't think this is a string, but it's not a string, but it's a string, but it's not a string, but it's not a string.",
      "reference": "Could we shorten this constant to maybe `FEATURE_USER_AUTH`?"
    },
    {
      "prediction": "I don't think this is a bug in this package.",
      "reference": "Any particular reason for 8? I feel like we could probably handle more..."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Try to use factory association declaration for default values, so it could minimal the line length. You may write in fetch_job factory like association :repository, factory: :repository."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Should the \"cancelled\" class be added regardless of the proposal's state?"
    },
    {
      "prediction": "I think this should be a `MongoClient` or `MongoClient`?",
      "reference": "nit: random whitespace change, let's try to keep these out of commits unless there are other useful changes."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `options.retainKeyOrder` and `options.retainKeyOrder`?",
      "reference": "Seems kinda dangerous - what if models length is different from paths length?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "set real one plz (get it from DB)."
    },
    {
      "prediction": "I don't think this is a problem with the `fpga_port_uafu_irq_set` type, but it's not a problem with the `fpga_port_uafu_irq_set` type.",
      "reference": "Should this be initialized to zeroes?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "The query is already built at this point, so I don't think this particular change actually helps wrt SOLR-10732? (and the `base.size()==0` case is already trivially optimized in `SolrIndexSearcher.numDocs(Query, DocSet)`)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "re-add the type in the annotation here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we simpify it as `cmd.Stderr = &bytes.Buffer{}`?"
    },
    {
      "prediction": "I don't think this is the case where the certificate is expired.",
      "reference": "there's enough \"nots\" in here that while it's correct by my review, I'd like to see a small unit test (just passing in an expired and non-expired cert)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with it.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The config option should probably have a more specific name. Also it's not for all gridded data but specifically for Images (and its subclasses)."
    },
    {
      "prediction": "I think this should be a bit of a hack.",
      "reference": "Be careful. This is not a preference but an option in a dialog."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "this will modify the incoming object, which may not be desirable in some cases. i think we should stick with the local var, override it with deployment.ClusterName if deployment.ClusterName not empty"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Is this not required?"
    },
    {
      "prediction": "I think this should be a `Blockly.BlockSvg` instead of `Blockly.BlockSvg`.",
      "reference": "You're using scare quotes on these terms instead of defining them."
    },
    {
      "prediction": "I think this is the default version of docker-compose required for ddev.",
      "reference": "These should both be const, not var right?"
    },
    {
      "prediction": "I'm not sure if this is the right place to save the settings.",
      "reference": "Can you catch a more specific exception here? Thanks :-)"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "This is a bug during handling the recover logic in `common chaos` controller, I fixed in this request when I found it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "During testing, we adopt the score threshold specified in the config file. Here the threshold is only used for visualization, and the variable name `score_thr` can be misleading. Renaming it to `show_score_thr` would be better."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `nav_menu`?",
      "reference": "can you make this `nav-primary` please? i'd like to roll with this since the `<ul>` class is `nav`, and primary is the name of the navigation menu"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@georgehrke Just out of curiosity. Couldn't you combine at least the combine the regex for '-' and '' with groups?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this is objectively better than looking up the object by name. As a follow-up, I'm going to see whether we do this name-based lookup somewhere else and switch to your method."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Why are you dividing by scale in the LTR case but not the RTL case?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Update after command rename"
    },
    {
      "prediction": "I don't think this is a good idea to use `googlesitekit.ModuleSettingsDetails-tagmanager` and `googlesitekit.ModuleSettingsDetails-tagmanager` as `googlesitekit.ModuleSettingsDetails-tagmanager` and `googlesitekit.ModuleSettingsDetails-tagmanager` as `googlesitekit.ModuleSettingsDetails-tagmanager` in `googlesitekit.ModuleSettingsDetails-tag",
      "reference": "I added this change to fix a bug with the legacy settings wrapper which was preventing it from working properly with the other modules  "
    },
    {
      "prediction": "I don't think this is the right thing to use.",
      "reference": "isn't AZKABAN_FLOW_VERSION_2_0 more explicit?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please don't leave an empty default"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the license.",
      "reference": "This isn't directly related, but the `import React from 'react';` below should be removed. We never import this directly and any modules from it we need are imported through `@wordpress/element`. This was probably added automatically at some point, but we also provide this automatically via `ProvidePlugin`."
    },
    {
      "prediction": "This is a hack, but I'm not sure how to do this with `brew update`?",
      "reference": "You can also use `echo: false` instead. Either is fine; I'm just pointing it out."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "what's the reason for this moved line?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't really follow what is happening here, but it looks like this _could_ conflict with the logic on the lines above... should this be an `else if`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`s => s.IsHidden == false` What's the purpose of adding this?"
    },
    {
      "prediction": "I don't think this is the case. I don't think this is the case.",
      "reference": "I would name this `clef-ethereum-address`. We already have a bunch of addresses in Bee, and people might wrongly think that this is yet another address"
    },
    {
      "prediction": "I don't think this is a test.",
      "reference": "you can just remove this"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we should avoid creating a dummy CR in the case of SPC. Please see if we can avoid this since we will not be patching anything in this CR."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Honestly not sure myself, but do you think it makes sense to move this conditional into the partial?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `temp_basedir` argument.",
      "reference": "As discussed in IRC (just so it doesn't get lost): This probably should be `-basedir-`, not `-prefix-`"
    },
    {
      "prediction": "I think this is a hack, but I don't think it's a better way to do this.",
      "reference": "basepath can be absoluta path and this needs to be supported"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Didn't get to the commit message"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "What about raising `ActionView::MissingTemplate` instead? That's what HighVoltage does."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is it kept for compatibility?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would find it pretty reasonable to add a MinerSigner method on the state view that puts these together."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It's stored in `PodDBAdapter.VERSION`. I usually use the expected release version code for that change. As this will be released in AntennaPod 2.2.0, the code would be `2020000`."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "What about method name itself? Do we run this for SQL too?"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack.",
      "reference": "`instanceUrl` should be `cs1.salesforce.com`. `communityUrl` would be `mobilesdk.cs1.my.salesforce.com`."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Let's use `if(name != nullptr)` to remove ambiguity"
    },
    {
      "prediction": "I'm not sure why this is a string, but it's not a string, but I'm not sure why it's a string, but I'm not sure why it's a string, but I'm not sure why it's a string, but I'm not sure why it's a string, but I'm not sure why it's a string.",
      "reference": "I wonder if it would make sense to have a separate namer for metadata? Metadata files tend to be expressed in a different language from the repo language, and have mutually exclusive concepts. So, `PackageMetadataNamer`."
    },
    {
      "prediction": "I think this is the default value for the `extraDataValidatorsAndVoteMustBeEmpty` property. I think this is the default value for the `extraDataValidatorsAndVoteMustBeEmpty` property.",
      "reference": "This rule is quite specific to qbft and so I don't think it should be part of the common rules. Would rather the common bft code didn't know anything about contract based voting/validator governance."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "This makes our life harder than it needs to be. A Set is unordered by definition. Please remove this method from Set and add it to SortedSet, but with no default implementation. We need to duplicate it then to LinkedHashSet but that's ok, it is the best we can do. Could you please add it also to SortedMap and LinkedHashMap? We are then able to close the original issue."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `response_headers` parameter.",
      "reference": "we can replace `for` with `params.update(response_headers)`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Any chance this is available in .NET Core 2.0 now?"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core.",
      "reference": "I wonder if it's necessary to let app pass in the context. What app level context should be sent? If no, is it enough for p2p agent to compose a context with network info there?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Why do we need both includes here?"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "SmartStoreInspectorTest expected results in a certain order"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think that you need something like `m_using_random_node.emplace(m_io_thread_pool->get_local_thread_id());`"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I don't think we need to maintain a separate set. The problem here is that the \"assignment\" that is killed for this variable is not really an assignment. If we just don't `assign` the variable with the non-existent value, it will not be reported. I pushed a fix."
    },
    {
      "prediction": "I don't think this is the case sensitive flag.",
      "reference": "Let me know if this is too pervasive. It is currently a private method in `BaseTableScan`. It seems both `SparkBatchQueryScan` and `SparkMergeScan` need to know the scan-specific split size when planning tasks. Therefore, I made it open. Another approach is to move all the `planTasks` logic to scan implementations, but for the combine tasks by partition feature, it requires grouping scan tasks by partition first, instead of returning them in an iterator fashion. I'm not sure if this is OK. `SparkMergeScan` also seems to re-implemented its own plan tasks logic."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Not sure what is this change doing?"
    },
    {
      "prediction": "I don't think we want to use `datetime.utcnow() + timedelta(minutes=30)` instead of `datetime.utcnow() + timedelta(days=90)`.",
      "reference": "this is funky. either don't take` minutes` as keyword arg or take both `minutes` and `days` and pass all of them on to `timedelta`. i'm guessing you're aiming for backwards compatibility, but i don't think it's worth it given how confusing this is. atlernatively, make `mins=60*24*30` the default. and that brings me to another issue, `mins=None` is not a very useful default."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please use a tab for indentation instead of spaces."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "I can't believe we didn't see this typo before :))"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is a good idea.",
      "reference": "If the logger isn't used, it probably doesn't need to be added."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "These files should in `/javascript/brython`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "minor, you can squash these into one `if`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Used regexes to do most of this, hence different methods of string creation of UUIDs. I plan to follow up with an additional change to remove direct references to google/pborman UUID so `uuid.New()` and `uuid.NewRandom()` will instead use our `primitives.UUID`."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Add a TODO here to revisit if this was problematic."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Note generally it -> It"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Is this relevant to this PR?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can we instead ensure that `opts[:run_in_parellel]` will always be a boolean? Otherwise we'll have to account for the case when it's a non-boolean value in multiple places, such as any/every other `if` statement."
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's not a string.",
      "reference": "Is this just moved out of the other files? It doesn't seem like this was generated like the other files."
    },
    {
      "prediction": "I think this should be a long?",
      "reference": "I started out doing everything `async`, but it was getting in the way of debugging, so I switched back to all synchronous until I got things working. We should probably move everything back to `async` and remove the synchronous versions."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this looks already too complicated..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "As for the testings, we better to verify the actual effects of the compaction. Of course, you could do it in future."
    },
    {
      "prediction": "I think this should be removed from the list.",
      "reference": "should we add a TODO here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `render` method.",
      "reference": "This can be inlined below as `GoogleSitekitDashboardDetails` is an unnecessary wrapper now."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "NewVHS -> NewVersionHistories this one looks better"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `executable_path` or `executable_path`?",
      "reference": "Is this `@missing_text` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Minor suggestion, but wouldn't it be cleaner to simply replace PACKAGE_NAME_FORMAT to all the optional path, then check that the path is empty in validate_package_name? We might also want a helper function to pull out the package name and sub-package path."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `editing` and `finishEditingFile` button.",
      "reference": "we should have a way to insert components into a i18n string. so that we could define a translation string like `'%{filename} is being edited'`, and inject the filename `<span/>` at the right place. I imagine there must be a language where the `Editing` text should come after the file name. we can think about that later tho."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Probably want break instead of continue."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was on purpose that I would set logging (NoLog=false) and a dummy logger below. The idea is to have better code coverage and test of debug/trace statements. Any reason you have removed this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "does adding a `Stream.<String>empty()` help here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is not being used anymore, so can be removed."
    },
    {
      "prediction": "I think this should be a string, not a string.",
      "reference": "Is it called some where?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Please remove this extra blank line."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "this is really the key, if you don't set this then gradle doesn't wire up the tasks that produce various files inside these configurations as inputs... I think we were just getting lucky before."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Sorry if I'm missing something here, but shouldn't this message be about failing to match with an *empty* selector, and/or perhaps even an empty *tag* instead of selector? The message seems a bit disconnected from what we're testing?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: please move these inside namespace."
    },
    {
      "prediction": "I'm not sure if we're in debug mode.",
      "reference": "may users try to abuse it?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why is this space removed?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can we remove this other line now then?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "There's a comma missing here at the end :wink:"
    },
    {
      "prediction": "I don't think this should be used.",
      "reference": "Why is this not required any longer?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `gogs/modules/base` or `gogs/modules/log`?",
      "reference": "Indentation seems a bit fucked up here. Run `go fmt`."
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "any chance in == nil? same below"
    },
    {
      "prediction": "I think this is a bug in h2o_sysfn. I think this is a bug in h2o_sysfn. I think this is a bug in h2o_sysfn. I think this is a bug in h2o_sysfn. I think this is a bug in h2o_sysfn. I think this is a bug in h2o_sysfn. I think this is a bug in h2o_sysfn.",
      "reference": "We would change the source code of h2o so that certain syscalls will be invoked through the `h2o_sysfn` macro."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "the name kTimelineCannotBeSignalled is confusing. It's not that a TimelineSemphore cannot be signaled... it's the \"VK_KHR_timeline_semaphore is enabled *variant* of the \"binary cannot be signaled\" message. We should probably have a consistent naming scheme to clarify. kBinaryCannotBeSignalledAltTimeline or hide the complexity in Get*VUID functions as needed somehow (pass in the extension structure?)"
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "Could you add a type hint? `percentiles: Optional[List[float]] = None`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `where` statement?",
      "reference": "Maybe putting ones they've used before first would be good, but this is fine for now."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I don't think we need these. Simpler just to put `routetable.TargetType...` inline below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why this instead of the old way?"
    },
    {
      "prediction": "I don't think this is the case for `LivelikeBreakCharmOnInvis` and `LivelikeBreakCharmOnInvis` and `LivelikeBreakCharmOnInvis` and `LivelikeBreakCharmOnInvis` and `LivelikeBreakCharmOnInvis` and `LivelikeBreakCharmOnInvis` and `LivelikeBreakCharmOnInvis` and `Livelike",
      "reference": "Just combining the inner if/else blocks like this is what I originally meant (I didn't mean replacing all the invisible checks in the outer if, I realize that would have been a functionality change regarding the rule) This should now be equivalent to `if (RuleB(Pets, LivelikeBreakCharmOnInvis) || IsInvisible(formerpet))` (the second check for the rule being false after the `||` would be implied, anything after the `||` would only be evaluated if the rule was false)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't want to write this back to the definition do we? Probably just want to create a local variable for it."
    },
    {
      "prediction": "I'm not sure why this is a good idea.",
      "reference": "Good catch! Could you please move this to `PlaybackService.this.onPlaybackEnded`? I think it's more clean if everything is in one single place."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We're trying to avoid X.org specific code. So I'm not a fan of this. Can't this be achieved in display server agnostic way?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This class can be removed?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `go-grpc-prometheus` package.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "To minimize the possibility of regret, perhaps we name this `ZapLogger`."
    },
    {
      "prediction": "I don't think this is the case for the `plan_name` field.",
      "reference": "This looks a little weird, but it's a feature of the gem we're using. You can give it a symbol representing the method you want called on current_user."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`Anomaly` imported here, but not used. Please run the changed files through pylint with nupic pylint config and fix pylint findings related to your changes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We needed this testutils file after all  "
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "line is 161 characters (from `lll`)"
    },
    {
      "prediction": "I'm not sure why this is a bug in Choos mesh.",
      "reference": "Please re-format/groupimport this line. You might need a little manual work."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "minor, you can just use `wf` instead of `worker.wf`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the original string, but I'm not sure if this is the right thing to do with the original string.",
      "reference": "I would suggest putting this in the resources directory with the same package as of this test class. Then you can utilize the method azkaban.utils.TestUtils#readResource to read it as string."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "could not import github.com/openebs/maya/pkg/upgrade/templates (invalid package name: \"\") (from `typecheck`)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "a official -> an official"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I only want the proxy request for this to run for kinesalite."
    },
    {
      "prediction": "I'm not sure if this.props.dateFormat is the same as this.props.dateFormat.",
      "reference": "White space boya?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe ditch these since `StackSummary` is not used anymore."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "suggest to indicate the value range & meaning in docstring"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "not sure if it works with prometheus by default, otherwise we will have to add this into prometheus config also"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "The rule renderer isn't meant to be stateful so probably best to move this out of here"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "passing in a `nil` here just so that the tests can pass in an alternative implementation seems weird, but I don't know what the convention is for doing something like this - @briandowns?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "IMO `dot` should be preferred. Remember `aXe`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Not a huge deal but this will block tests, also, don't they stay open by default now?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could you make it a local constant for now ?"
    },
    {
      "prediction": "I'm not sure if it's a string, but I'm not sure if it's a string.",
      "reference": "What is this `collection_id` field here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is there a reason why we don't use logging for this?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Exceptions should be placed in application layer -> infrastructure is aware of application - not the other way around"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "IIRC issue mentioned reporting _symbolic message_ - so in this case it would be `line-too-long`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Is this intended to be `spells[spell_id].reflectable` here? Edit: Should be `spells[spell_id].feedbackable`, right?"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "How should we set this for existing teams?"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "It would be nice if we could verify that this is in fact the error we expected. But that's a latent issue, something for the backlog."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I hate then some internal process specific middleware leaks into connection manager :( todo later."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "Reflects where these files were moved for `pkg_resources`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `Ember.computed`?",
      "reference": "This should be computed('i18n.locale'...."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can you explain to me what goes wrong here? Can the test be adjusted to set up working routing instead?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We can get rid of this import then."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure how useful is unlock event."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Consider make the second argument a `encoderOptions` which includes the `lowercaseFields` just like opening a collection."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is the value of renaming this to `ctx`? We generally prefer the longer names because they are easier to read and to type."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hm. This could be a case of left-sided driving, having u-turn lanes on the right side. Good catch, but looks good to me."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There was a [JsonPropertyName(\"success\")] here it did serialize fine for me, so I am not sure what was the matter? Also maybe uppercase?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "we can just use read env here, pretty sure"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Could you replace local hook with global hook `afterModifyTransformStart`?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `_files.keys()` method.",
      "reference": "You seem to be basing your PRs off an commit, which keeps reintroducing these changes, which makes it harder to review your PRs."
    },
    {
      "prediction": "I'm not sure if this is a mocha callback?",
      "reference": "Maybe it would simpler to ignore opt_port if type !== 'number'?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "As far as I can tell, `IDictionary<string, object>` implements `IEnumerable<KeyValuePair,string, object>>` so we are just making it more generic. From the issue, I understood that we want to maintain sequence/order. I believe `IEnumerable<>` won't fix the issue."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change prevents a user understanding how their server is configured. Best to leave at `info` level."
    },
    {
      "prediction": "I don't think this is a bug in this package.",
      "reference": "I will add the following to the list: - api.SpecScale - api.SpecSticky"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "As defaultSendPort is being removed, and I don't like TODOs on examples, please remove the whole line"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "since we are now no longer expecting an input of float to return an empty string, i have removed this test case."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "It would be cleaner if you were to pack the name&desc in a `MetricName` and pass it to `MakeCounter`"
    },
    {
      "prediction": "I think this is a bug in Jaeger.Tests.",
      "reference": "Do you know why do we need this?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I guess this using is what causes the build to fail"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I like the explicit unregister approach."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "We should able to use 0x30 as summary, and make 0x80 reserved for future."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This allows strategic exclusion of http spans."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with this, but I'm not sure why this is the right thing to do.",
      "reference": "why not just `string[]` instead of nullable"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How does this work? Why isn't each tag after the first picked up as a new arg/flag?"
    },
    {
      "prediction": "I think this is a bug in the traced application.",
      "reference": "This key is actually yet to be determined. Meeting with the backend team and Garner to discuss."
    },
    {
      "prediction": "I think this is a bug in VkImageView.",
      "reference": "Why remove the crash protection? We're just going to get a bug filed on it."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe be consistent and name it `FRAME_OPTIONS`."
    },
    {
      "prediction": "This is a hack.",
      "reference": "This check/exception is a guard for the next few lines of code. It shouldn't be necessary now. In fact, I don't think you need the if (parentConnection.type == Blockly.INPUT_VALUE) branch at all."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could probably move these constants too?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe 'failed' instead of 'missing'. Also do we really need to write ticket numbers here?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Test used to use old bouncycastle dependency which isn't needed anymore from Hadoop. Switched to use builtin Java split."
    },
    {
      "prediction": "This is a hack.",
      "reference": "nit: I think this would be more readable as \"Some language names contain Unicode characters\"."
    },
    {
      "prediction": "I think this is a bug in the GNU General Public License.",
      "reference": "Thanks for adding the header, but I don't think 2017 is a very accurate guess here. Could you do a quick search with git blame and change this accordingly?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Oh interesting - does web-test-runner not resolve package.json files?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is there a way to derive this value from the locale itself? I feel hardcoding the prefix in the props isn't the right approach, but I'm not sure what the locale file contains exactly."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I'd much rather see these warnings in our devtools (`debug/index.js`). Strings contribute quite a bit to our file size and moving them there would prevent bloating core."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Use `String.format(Locale.US, ...) to avoid the `Lint` warning."
    },
    {
      "prediction": "I think this is a bug in v1.Service, but it's a bug in v1.Service.",
      "reference": "nit: ServiceReference represents a reference to a v1.Service."
    },
    {
      "prediction": "I think this is a bug in GcpChaosSpec, but it's a bug in GcpChaosSpec.",
      "reference": "since it changes to the array, how about change the name to `DeviceNames`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the top level property.",
      "reference": "Can we avoid this. upgrade engine code should take care of this."
    },
    {
      "prediction": "How to do this?",
      "reference": "should also be alphabetized or at least grouped and alphabetized within group"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "No need for this, as pylint already only turns things off for this function and it's needed for the entire function."
    },
    {
      "prediction": "I'm not sure why this is a bug in the future, but I'm not sure if this is a bug in the future, but I'm not sure if this is a bug in the future, I'm not sure if this is a bug in the future.",
      "reference": "nit: can we remove \"can't\" from the error message?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "instead of modifying 'Status' which impacts the state diagram, how about using some annotations on CVR? This can probably help for our upgrade as well. Is this possible? cc: @AmitKumarDas"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Rename this as KubernetesGPGURL - >KubernetesUbuntuGPGURL , Modify it where ever it is used."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "I'm not totally sure I like the idea of putting a default fee here, but I guess so long as we make sure to track the default fee of bitcoin core, we're good. We should really also take a look at the byte size of the transaction, and use that to determine what the fee should be. But that could also be a different PR."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "oh yeah, `tail`, `update`, `prepend`, `append`, `subSequence`, `trim` just became effectively constant (without memory leak) :)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Can you add back a deprecated `destroyLinks` method for backward compatibility? It can simply proxy `destroyResourceLinks`, and we can remove it in the next major release."
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "A reminder that we should discuss whether to rename this to \"sockets\" or \"listeners\"."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with eprosima::fastrtps::rtps::RTPSDomain and eprosima::fastrtps::rtps::RTPSParticipantAttributes.",
      "reference": "Why do you need to include this using declaration?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "@halter73 where is this file generated from?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What do these `#if TRUE` accomplish?"
    },
    {
      "prediction": "I don't think this is a bug in OpenTelemetry.",
      "reference": "Probably a good optimization to have this, but I don't think it's strictly required. For \"legacy\" Activity flows we pass them through an ActivitySource for sampling. So the logic below should also catch these?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@jessieay Intentionally moving away from passing a param?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think you could condense this code considerably by getting rid of the initialization and foreach loop and simply saying: `$firstname = trim(implode(' ', $nameArr));` What do you think?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "hmm, we actually should _add_ `'use strict'` everywhere  "
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "it's not just fetching override properties here, right?"
    },
    {
      "prediction": "I think this should be a good idea.",
      "reference": "Is it worth logging the error?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "What's the point of this class?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I'm being picky here, but I think I would prefer `toggle` to be kept here and just change the condition to `contentType !== 'movies' && contentType !== 'mixed'` or `!['movies', 'mixed'].includes(contentType)`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please put this down with the other \"github.com\" imports."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Minor but probably want `push_front_preference` to have a trailing `_a` to be consistent with the other parameter"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, not a string.",
      "reference": "Nit: the formatting is a bit off. I would expect this to be 2 indentations from `this.expr = ...` but this is 8 spaces, not 4. Also, most places leave the `);` on the last line of the method arguments."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Ack, @chrisdunelm snuck this class extension past me. This is not a pattern I want to have used..."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `flush_endpoint_enabled` option.",
      "reference": "nitpick: I wonder if we should name it `flush` only (?)"
    },
    {
      "prediction": "I'm not sure why this is the case, but it's not the case.",
      "reference": "Why gauges, not counters?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Just making a note here that this may break pre GWs between pre 2.2.0 and 2.2.0 servers. Not sure, will have to experiment/dig a bit more."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Shall we rename this status to CONTAINER_FAILED? ^^ cc: @sshardool"
    },
    {
      "prediction": "I don't think `done` is actually `true` or `false`.",
      "reference": "Thinking out loud here: I believe the only reason we need `peer.ID` as a parameter to this method is because we are not persisting blocks from pubsub (instead we are refetching them). If nodes persist the blocks they received over pubsub then I think we can guarantee peers we share a connection with (i.e. that are in the peer tracker) will always have the blocks we are fetching (else how would have we gotten the pubsub message). I imagine the concept of an `initialPeer` can go away once #2962 lands since the peers in the tracker will have the block. Although I don't think that covers the case of fetching blocks our peers have deemed semantically invalid and thus not stored..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I know it has no effect but my eyes can't help. Is that line not too long?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does that mean we disable service loop prevention for packet generated by local host?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `cygwin_installed` flag?",
      "reference": "It seems a little odd to have both `host.is_cygwin?` *and* `host.cygwin_installed?` defined (with a possibility of having `is_cygwin?` be `true`, but `cygwin_installed?` returning `false`). Do the docs clearly explain the difference?"
    },
    {
      "prediction": "I think this is a hack, but it's a hack, but it's a hack, but it's not worth it.",
      "reference": "Does this mean manifests will be written with the v2 schema (i.e. with sequence numbers) even though `TableMetadata` is v1 and the manifest list is written with v1? And this should work because we do a projection on read and sequence number is optional?"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's a string, but it's not a string, but it's not a string.",
      "reference": "Should we be sharing this property key with the read? Maybe it should be belong to the file-scan-task object itself?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Nice! Good idea to move these out of the main struct."
    },
    {
      "prediction": "I don't think this is a bug in ddev.gitignore.",
      "reference": "Thanks for paying attention to other places this might happen. This one is particularly important; I probably never should have gotten in the habit of CheckErr(), since it does a log.Panic() explicitly, which looks like something else until you look closely. It's supposed to be used places where \"can't happen\" but Things Can Happen."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Converting this to an enum makes it obvious that I combined things that don't really belong together. It would probably be better to create two enums `StoreType` and `TransportType` (in more appropriate locations). That also makes it necessary to have (at least) two `ServerSettings` classes. `IncomingServerSettings` and `OutgoingServerSettings`. Also, the naming is inconsistent. Maybe it would be better to make the string that is used for import/export explicit, e.g. WEBDAV(\"WebDAV\")."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It's out of scope for this PR, but I don't find this utility's name to be particularly intuitive. It speaks to nothing of what it does. Does it create a token list? Process one? Get one? `tokenListToArray` would be nice."
    },
    {
      "prediction": "I don't think this is the right thing to do with this.data('has-label');",
      "reference": "The message for this check used the existence of a label to determine the output, which doesn't work with the current schema. So I updated it since the data only needed to know a label was present and not what it was."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit: \"The current project does not have requested application\""
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Extend Unit test for this class"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "This is this a copy / paste error from above."
    },
    {
      "prediction": "I'm not sure if this is a type interference, but I'm not sure if this is a type interference, but I'm not sure if this is a type interference, I'm not sure if this is a type interference.",
      "reference": "this package has to be renamed to `typeinference`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This cancels the above null-check I guess."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "change to timerIntervalInMillis"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "`any rules` should be `any roles`"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Why does the method need to be renamed? I would just keep the old name and update the other uses (which are only tests). That way, we can reduce code duplication."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "I'm not sure if this is going to work - I think it's fine to keep them hardcoded here, as the statusbar can still show `:`, `/` and `?` even if the key is rebound."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@tmetzke shouldn't we replace this library with the `2.12.1` instead of removing it?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "uint64 seems excessive here. Should we reduce to a uint32 @whyrusleeping ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hmm, I thought this was getting used. These are used elsewhere as a cached value (in `svc deploy` it's `o.targetApp`) but I guess since storage doesn't actually need to validate that the app exists, just that there are local services, we never used it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "To keep it simple, how would you feel about just using r.RemoteAddr? Since every request comes through here I want it to be as lean as possible. Frankly I'm OK with the port showing up in the log; maybe it'd even be useful to someone."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "grant bonus depends on both `admin{}` stored in statedb, and `P2Start/End` in local struct, which is kind of weird at Kamchatka height, we add the bonus Start/End epoch into `admin{}`, so it solely depends on `admin{}` stored in statedb"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Use single quote to wrap the str."
    },
    {
      "prediction": "I don't think this is a problem with the current state of the whitelists.",
      "reference": "Is the plan to rename this later?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is there a reason why we need a special case for Email at this point? Is the idea that other methods can turn into Email even if it's not configured as a top-level option?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "This wording is a bit ambiguos, I first thought it meant the directory has no entries in it. maybe \"dir\" -> \"dir string\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we need both `HPX::m_hpx_initialized` and `HPX:: m_was_initialized`?"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "also check RPCName?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Remove unused import"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I assume there will never be a scenario where justValidate is expected to be true on a restart"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Report listeners are synchronized, even 'though the cache is thread-safe... I've not profiled it, but it may be a cause of contingency. Any better way around this? Also, do listeners **really** need to be synchronized? Can't we just make them thread-safe?"
    },
    {
      "prediction": "I'm not sure why this is the default value for the compiler.",
      "reference": "I don't think this is correct. When `compiler` is not given in `.travis.yml`, the announcement will be `--version`, which results in \"`command not found`\" (though not critical), and the cache slug will lack this information (also not critical)."
    },
    {
      "prediction": "I think this should be a `Promise` instead of `Promise.resolve`.",
      "reference": "Why do this rather than `args = []` in the function signature?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I think we probably *should* do validation of whether there is a suitable implementation if local-validation is true. I'm not sure how useful that actually is though"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@StrikerRUS here may need to concat two data by col."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why the space?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "please resolve the extra indentation"
    },
    {
      "prediction": "I don't think this is the case for the `previous` parameter. I don't think this is the case for the `previous` parameter. I don't think this is the case for the `previous` parameter. I don't think this is the case for the `previous` parameter. I don't think this is the case for the `previous` parameter.",
      "reference": "More proof that this check is needed always."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "`m_al_comms` now contains smart pointers."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Did you do a test run with the compare script? I'm nervous about what happens on all the generators..."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "For a client, we store host, as string c.host. That is what we use for monitoring and statsz. Not sure if its useful here or not. Looks like probably not."
    },
    {
      "prediction": "I think this should be removed.",
      "reference": "This change is suspicious. Why did the number of partitions increase?"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `slug_matches?` method.",
      "reference": "I'm still new to this area, so please forgive what may be a stupid question: When would this be false? And do we have a test for that situation?"
    },
    {
      "prediction": "I think this should be changed in the future.",
      "reference": "Should there be any changes to this file at all?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The only field being used is the KeyType; Instead, we can probably just make a `keyType` variable here."
    },
    {
      "prediction": "I'm not sure if this is the case with the `credentials` option, but it's not the case with the `credentials` option.",
      "reference": "This should be done by code-gen change happening in the hydra repo. I am tweaking it just to get CI into a 'passing' state"
    },
    {
      "prediction": "The `setupRegistry` option is deprecated, please use `setupRegistry` instead of `setupRegistry` instead of `setupRegistry`.",
      "reference": "Cleaned up when I originally added support for passing `screenContext` here (and later `viewContext`) but that was removed."
    },
    {
      "prediction": "I'm not sure if this is a C++ mangled name, but I'm not sure if this is a C++ mangled name.",
      "reference": "This looks like a bunch of whitespace fixing that's unrelated. Can you revert?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `new Sensio\\Bundle\\FrameworkExtraBundle\\SensioFrameworkExtraBundle` and `new Sensio\\Bundle\\FrameworkExtraBundle\\SensioFrameworkExtraBundle` and `new Sensio\\Bundle\\FrameworkExtraBundle\\SensioFrameworkExtraBundle` and `new Sensio\\Bundle\\FrameworkExtraBundle\\SensioFrameworkExtraBundle`",
      "reference": "should be removed instead"
    },
    {
      "prediction": "I think this should be a test case, but it's not a test case.",
      "reference": "should use randomization ?"
    },
    {
      "prediction": "I think this is a bug in cobra.",
      "reference": "returning nil because we want to mayactl to exit with 0 status code."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this change relevant to the PR? (and I believe we should use `text/plain` considering the fact that it can be displayed using web browsers...)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`[Flags]` is now auto-generated by an argument to the `EnumHint`. (The attributes happen to come out in this order. I don't think it's worth controlling the order.) #Resolved"
    },
    {
      "prediction": "I don't think this is the right thing to do with the syncer.",
      "reference": "I think same here - in general we don't need to use Setters / Getters since configParams isn't a public API."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why using `fmt.Sprintf` where `fmt.Sprint` would do the work (notice no `f` in function name)?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `current` attribute.",
      "reference": "Extraneous blank line."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "nit: syntax : neither -> nor"
    },
    {
      "prediction": "I don't think this is a bug in the future. I think this is a bug in the future.",
      "reference": "Is it safe to assume that these two keys are always present? `this[string]` will throw a `KeyNotFoundException` if they are not."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Is the `flowDefinitionId` sufficient to uniquely identify the flow or does it need to be the tuple `<flowId,flowDefinitionId>` ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Shouldn't it be in the reverse order? `DateTime::createFromInterface()` returns `self` and accepts `DateTimeInterface`."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "this check is now redundant. The rest of the function downwards basically does the same thing but with safer checks."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please could you remove the useless space."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "What's the point of this block (and isn't it effectively dead code)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Newline at end of file plz"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Can this be refactored to avoid including the aws sdk in the types that we expose? I know it's not being exposed directly through the types we expose, but I do worry that it might make it easier to accidentally do that in the future and not realize it as easily."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the index queue.",
      "reference": "Hi thomas, i would propose to indicate in the name, that only the indextime is updated, otherwise somebody might think the whole items is getting updated. I would propose something like \"updateIndexTimeByItem(Item $item)\""
    },
    {
      "prediction": "This is a hack.",
      "reference": "This is not the right exception class. There is an InvalidSelectorException class that covers bad locators."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I assume this came from format?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "I'd suggest a default value of `false` just to make sure existing tasks are ok when they get deserialized after an update to a version containing this code."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we really need this? Seems like it would pollute the logs pretty badly."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "`Vector<byte>.Count` should Jit to const when intrinsic; not sure when `Vector.IsHardwareAccelerated == false` ; however we know `readonly static int` does Jit to const."
    },
    {
      "prediction": "I don't think this is a bug in sqlalchemy.",
      "reference": "Can we use a skipIf decorator instead?"
    },
    {
      "prediction": "I don't think this is a bug in Faker::Number.number.",
      "reference": "Missing version tags"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think this should also filter out `validate_resolve_reference` hooks."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with OpenTelemetry.Exporter.OpenTelemetryProtocol.Implementation.",
      "reference": "unrelated, but required fix as metrics branch got broken with the latest main->metrics merge and conflict resolution."
    },
    {
      "prediction": "I think this is a bug in the GNU General Public License.",
      "reference": "Feel free to remove this line"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "~~Should this match the key updated above?~~ :+1:"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`gofmt` allows a more compact form `defer func() { _ = f.Close() }()` or just add `// nolint:errcheck` before `defer`."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `miner create` command.",
      "reference": "collateral is in FIL"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should not create channel of node which are not connected."
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think the docstring should say something like \"Alias for the `source` option\" or something similar."
    },
    {
      "prediction": "I don't think this is the right thing to do with it.",
      "reference": "Please use properties without suffix `_fr` so they can work across different languages as @teolemon mentioned"
    },
    {
      "prediction": "I think this is a bug in h2o_httpclient.c.",
      "reference": "Declaration here is `static` but the definition at the bottom is non-static?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Hi @myml, thanks for the contribution! `blob` and `blob/driver` are both in the same module, so you shouldn't need to split this change up into multiple Pull Requests. Also, I'd like to see it working, including the implementation for `s3blob` and `gcsblob` (these should be easy, just pass-through to the provider) and `fileblob` (might be trickier...), and a test in `drivertest/drivertest.go`."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Was it a bug?"
    },
    {
      "prediction": "I'm not sure if `attr_value['string'] is not None` and `attr_value['string'] is not None` and `attr_value['string'] is not None` is not required as `attr_value['string'] == value`",
      "reference": "# `attr_value['string'] is not None` probably not required as `attr_value['string'] == value` check is already being done"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "You're accessing private variables here - `last_hovered_link` should be public in `TabData`. As for `tabbed_browser._now_focused`, I think you can use `tabbed_browser.widget.currentWidget()` instead."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `Microsoft.Azure.TestUrlExtensions` class. I'm not sure why this is the right thing to do with the `Microsoft.Azure.TestUrlExtensions` class. I'm not sure why this is the right thing to do with the `Microsoft.Azure.TestUrlExtensions` class. I'm not sure why this is the right thing to do with the `Microsoft.Azure.",
      "reference": "We should file a bug for this - we don't need the extensions class if there are no operations on the client"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is it possible to import from k8s instead of copy in? :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`@param float` can be dropped here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "maybe we can leave this change un-reverted."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "I wouldn't make MethodDeclarator an AccessNode, nor an Annotatable. It's the MethodDeclaration that can be annotated, and has info about the modifiers, and is already an AccessNode"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `player.headicon` property?",
      "reference": "delete this class"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Replacing `+` (1 or more) with `*` (0 or more) would've also done the trick."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I've been meaning to fix this for a while. Thanks."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "This is adding multiple processor pipelines. I guess you wanted to add multiple processors to the same, single pipeline?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "If you need str(x[0]) here, you'll probably need str(x) the line after that I suppose. Also, shouldn't we use `raw()` here instead of `str()`?"
    },
    {
      "prediction": "I think this is the default value for `batch_write_lock_ttl`?",
      "reference": "3.6 seconds? what does it stand for?"
    },
    {
      "prediction": "I don't think this is a problem? I'm not sure if this is the case.",
      "reference": "If the command fails, is stdout nil or \"\"?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why is api-version now removed in the generated code?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "We may register all built-in optimizers of PyTorch here to simplify the builder."
    },
    {
      "prediction": "This is a hack.",
      "reference": "No need for this new variable."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "doesn't this enqueue a double render or is that safeguarded somehow"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "But now you may get DATA RACE reports because c.acc is sometimes changed. I wonder if we should not rework that whole sending subs through route."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with ADIOS.",
      "reference": "Use `ADIADIOS2_HAVE_HDF5`, not `ADIOS_HAVE_PHDF5`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Would be nice to put this in a separate context named `\"with a string and a non-string\"` (since that's what it is -- it's definitely not a non-string and a string!)."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Should MAX_PERTABLE_ENTRY here be 10 ?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Should move these out of frame into a static class? Similar to reason phrases?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "That means we still create `UseLane` instructions but threat them like `Suppressed`? Can we maybe change this in the pre-processing so that we will just emit `Suppress` instructions in these cases?"
    },
    {
      "prediction": "I'm not sure why this is a bug in iotexproject, but I'm not sure why this is a bug in iotexproject.",
      "reference": "no need to move here, iotex-proto is outside of iotex-core and considered same as iotex-address, go-pkgs"
    },
    {
      "prediction": "I think this is a bug in X86_64.",
      "reference": "Looks like a clang-format style violation: should turn Travis red."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think we need some YARD docs here, particularly to list all the color symbols that are valid. Otherwise users will have to look at the source to discover that."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Not sure if this needs a doc block or not since it's completely internal, but   for cleaning this up. (@felixarntz docs?)"
    },
    {
      "prediction": "I don't think this is a bug in libgbenchmark.",
      "reference": "The change here is to address what exactly?"
    },
    {
      "prediction": "I'm not sure if this is a MSI environment, but I'm not sure if this is a MSI environment.",
      "reference": "Is this really an Option? IIUC, you compute it automatically for the URLOpener case, why would we require a user to fill it in when using the constructor? I.e., can't we drop this and use `adal.MSIAvailable` instead? If that call is expensive, cache it on `bucket`, not `Options`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Was this done automatically or by hand?"
    },
    {
      "prediction": "This is a hack to make sure that the target is not in the current group.",
      "reference": "This looks like it will only work for the first child, since after that we've overridden `desired_group`. Should we have a separate variable for this?"
    },
    {
      "prediction": "I think this is a bug in VkCoreChecks::PostCallRecordCreateDevice.",
      "reference": "Should this be a constant somewhere?"
    },
    {
      "prediction": "I don't think this is a bug in OpenTelemetry, but I don't think it's a bug in OpenTelemetry.",
      "reference": "nit: sort alphabetically."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Now, It's redundant, I suppose."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "nit: The format recognized by tooling is `// Deprecated: [..]` so you likely want this to be, // Deprecated: Use \"go.uber.org/yarpc/peer/peerlist/v2\".Implementation instead."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: 1. when formatting input strings, make sure to place them in quotes so we could identify white space issues. i.e. '%s' 2. If there is untyped, non-nil error, you want to log the error string as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe this can be fixed with the original code if you just omit the \".dll\" file extension so it reads `[DllImport(\"Datadog.Trace.ClrProfiler.Native\")]`. On Windows it would look for `Datadog.Trace.ClrProfiler.Native.dll` and Linux/Mac it would look for `Datadog.Trace.ClrProfiler.Native.so`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "couldn't we just read the boolean as a string (I would assume that this return \"true\" or \"false\"), migrate if to its new value and keep using the same pref key?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "If these variables are only used in main function, move these to the beginning of that function. If there is a foreseeable reason to have them as global statics just let me know."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "This one was wrong."
    },
    {
      "prediction": "I think this is the case where `allAffectedNodeIDs` is not a list of all the node IDs.",
      "reference": "What happens if nodes throughout a hierarchy are modified (as they would be)? It looks like we're going to `Reset` once for each `NodeID` affected."
    },
    {
      "prediction": "This is a hack.",
      "reference": "> Note that allocation of vmheap fails upon initializing dynamoRIO 64 on WoW64 processes. Thus, we need to pass -reachable_heap to avoid having to make this allocation. This should be solved by changing the default `vmheap_size` to be much smaller than 8GB for x64 DR inside WOW64."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Is it really worth expanding our public API for this? After all, isn't calling this the same as calling `notification.fully_formatted(...).lines`? If so, I'd rather not widen our API (and thus, increase our maintenance burden) when it's so simple to get all the lines already."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is it necessary to keep this class around just to define this constant? Or can we place it somewhere else?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Question - do we cache NetworkPolicy itself? If so, here we can point to NetworkPolicy?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "For my view, `Register` means the process of **insert node resource to etcd through api-server**, which is called by upstream rather than here, how about changing the func name to `OnConnected`?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "I would prefer an active verb for this property, e.g. `initializeTelemetry`. The reason is that this property refers to something the engine does once on startup. Other properties that use passive voice (e.g. `authorizationEnabled`) refer to a state of the engine during its lifetime."
    },
    {
      "prediction": "I don't think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string.",
      "reference": "please use new line to maintain reasonable line width"
    },
    {
      "prediction": "I don't think this is the right thing to do with the context.",
      "reference": "I would skip this check or add an internal server error response."
    },
    {
      "prediction": "I don't think this is the right thing to do with `config.notarize` and `config.notary_user` and `config.notary_password`",
      "reference": "missing `{` here (and then `}` after `notary_password = config.notary_password`); it's only going to do the first one"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is odd because it's actually in our generated SiteSettingsPath, not in the SiteLocalSettingsPath (wp-config-ddev.php). Are these two files swapped somehow? I'd expect SiteSettingsPath to be wp-config.php and SiteLocalSettingsPath to be wp-config-ddev.php. BTW, I'm *way* ok with renaming that to SiteDdevSettingsPath."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It seems like this must necessarily be a stopgap. Can you please add a TODO(#xyz) to point to the appropriate issue?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is the return signature necessary since we never actually return if there is a problem (I'm referring to the call to `logrus.Fatalf`). Let's pick a pattern and stick with it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@btecu why is this override needed here? I'm not seeing a `new` being used here."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Should it not be more something like: `MaxAccountConnectionsExceeded` here?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "minor: use a non-default CE service account for testing (since default is handled in a specific way in the code)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is how I ran the 512MiB test. It's probably too much data for a fixture, and makes for longer functional tests (although still less than a minute on my laptop)."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "So we weren't able to hide the fact that the file wasn't pre-generated and had to introduce this \"option\" to detect that?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Agree that exporting these maps is the best tradeoff, just registering my ongoing discontent with the lack of `const` collections."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "This could probably use `const` as well?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "it doesn't look like these need to be exported?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I think you should remove \"fmt\" here. And change `fmt.Errorf` to `errors.Errorf`."
    },
    {
      "prediction": "I'm not sure why this should be added to the database?",
      "reference": "Here's the `resources` attribute @jferris. I'm not against renaming `Product` to `Resource`, and this one... something else."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "If the context is unused, this is equivalent to `var wg errgroup.Group`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "very minor: I'd prefer these two added rows are switched so that fragsizeIsMinimum directly follows fragsize"
    },
    {
      "prediction": "I don't think this is a local interface.",
      "reference": "Given that 115 returns `True`, why would this be `False` here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please move this test method just below `oauth2LoginWithOneClientConfiguredThenRedirectForAuthorization()`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why this new configuration?"
    },
    {
      "prediction": "I think this is a bit of a hack, but I'm not sure if this is the case.",
      "reference": "I don't think that we need to check `hasArray` here. I think the reason why this didn't previously check `hasArray` is that the array passed to `DataByteArray` must start at offset 0 and be valid through the array length, so a copy was needed in almost every case. It may be simpler to change this to use `ByteBuffers.toByteArray` and pass the result to create `DataByteArray`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`spanReference` -> `baggage`  "
    },
    {
      "prediction": "I don't think this is the right thing to do with `/-/verdaccio/logo` and `/-/verdaccio/logo` as `/-/verdaccio/logo` and `/-/verdaccio/logo` as `/-/verdaccio/logo`",
      "reference": "Why the `/-/verdaccio/` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Has been waiting for a million years "
    },
    {
      "prediction": "I'm not sure if this is a valid enum value for path `{PATH}`.",
      "reference": "Minor grammar detail: the 'than' is unnecessary"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think you can just simply fix this line to `self[:2].to_pandas()`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "if we are returning the `ws` here when passing in `se:cdp` we can just return it straight or do we have to make a request to get the `ws` address?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `googlesitekit/datastore/site` or `googlesitekit/datastore/site`?",
      "reference": "I could add a resolver for this (like above) but it seems more sensible to just change the one reference!"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "not sure \"actual\" adds value - secondsSinceParent is probably closer."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Line is too long. [94/80]"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "The error should be `At least :number items are required`"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "singleCaseSwitch: should rewrite switch statement to if statement (from `gocritic`)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Could combine this with `encryptionKeyGetter` to have a single `keyGetter` interface. I'm not sure which way is better."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Is there any security issue here? If we integrate with Hive security (and I don't know if we have or not) is there some notion of re-authentication at connection time?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Does this mean we do not support writeConcern on `createCollection`?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I guess `sid` was for `sessionID`, but now it looks strange: `sid.ID`."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "We'll need `infrav1.SecurityGroupBastion` as well"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This `fileName` should probably be `remote` and be relative to the Fs root as per normal rclone usage."
    },
    {
      "prediction": "Should we remove the index spec?",
      "reference": "That way we are back to having just one index on k_0 So we can really compare the execution times with and without re-indexing"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Expression that uses a negation pattern to exclude all characters that aren't in the expression."
    },
    {
      "prediction": "I don't think this is a valid value for the `Rpc-Both-Response-Error` header, but it's not a valid value for the `Rpc-Respond-Service-Header` header.",
      "reference": "Similar to my suggestion for HTTP, let's remove this and use `ServiceHeader` instead."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "The serviceDirOnHost[0:1] was completely wrong. It wasn't just Windows, glad you got this fixed!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would membership take 10+ seconds to detect the failed node?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "hmm, in this case perhaps the whole try-except could be removed altogether? because if the file does not exist, it's already returning `None`. In any other case it should actually probably fail with the exception, no?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This function does not need to be public"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "  Any chance we can get a CSS class for this? I know it's just in one place but feels like a dangerous precedent to set."
    },
    {
      "prediction": "I don't think this is the case for the `nextMethodName` attribute.",
      "reference": "> && this.Extensions.ContainsKey(\"nextMethodName\") [](start = 96, length = 48) From line 124, looks like we don't need `&& this.Extensions.ContainsKey(\"nextMethodName\")` condition or we don't need line 124 #Closed"
    },
    {
      "prediction": "I don't think this is a good idea to use `vnode.props.ref` instead of `vnode.props.ref`.",
      "reference": "Moving this code from compat to core shaves 47 bytes out of compat and only adds 6 bytes to core so I thought it was worth it."
    },
    {
      "prediction": "I'm not sure why this is the right thing to use.",
      "reference": "Please use \".NET Core 3\" - i'm trying hard to use one form, and this is the one MS advices"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Unrelated to this change, but this is a fix for when TestDoStartCgroupInitHappyPath has a failure after the test goroutine has already exited."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Hmm, I'd really expect this to work, and yet it doesn't. I'll investigate later, though it might get Monday until I get the time."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this changes affect process building dynamic libraries anyhow?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Could you limit what is imported here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "just to clarify - on line 1074 we update `zip_file_content` for non-local lambdas, but never store it, which means lambda never picks it up"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Golang naming convention is to use camel case `icmpPktWithTypeCode` Often the linter will complain"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We can do away with assigning the response here too."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Bumping the newViewportHeight"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Is this change correct? Looks like a typo and not sure this should be changed?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I checked the tests coverage and strangely it look like those three lines are not covered (?!). Do you have the same result on your side ?"
    },
    {
      "prediction": "I think this is a bug in MathBenchmarks.",
      "reference": "nit: please try to avoid changing end of the file (it adds a noise to the code review, but does not provide too much value)"
    },
    {
      "prediction": "I think this is the only way to do this.",
      "reference": "I don't see the \"only\" part reflected in the code but maybe I'm missing it. Also, the indentation is misleading: the `.SelectMany` calls are perfectly aligned but are *not* operating on the same \"level\". I'd expect the second `SelectMany` to be on the same height as the inner `Where`, just break `pathObj => pathObj<HERE>.Where` and lines won't be that long."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It seems like most of these will never be nil, are they optional just in case?"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to test the correctness via decodeRow.",
      "reference": "`.addColumn(\"c1\", IntegerType.INT, true)` means `PkHandle=true`, maybe should add `.setPkHandle(true)` in line 31"
    },
    {
      "prediction": "I think this should be a long type, but it's not a long type.",
      "reference": "how about `Cannot encode row key with non-integer type` directly?"
    },
    {
      "prediction": "I don't think this is the case for the `fetchActiveFlowByExecId` method.",
      "reference": "The method names `fetchUnfinishedExecutions` and `fetchUnfinishedFlows` are too similar to each other. Would it be better to use the name `fetchUnfinishedFlowsMetadata` since you are only fetching metadata info about the flow?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Note that `sudo` is not available by default on BSDs; there are a few places in the codebase here where that's explicitly worked around by using `su`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "ultra nit: missing Oxford comma :P"
    },
    {
      "prediction": "This is a hack.",
      "reference": "This is not supported in Spark 3.0.0-rc2 yet. I'd skip this for now."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "BLOCKING: Why does `Query` return an `*exec.FunctionSignature`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "please move this down to immediately above the assignment to `c.dirtyBcache`"
    },
    {
      "prediction": "I don't think this is a problem with the `blob://myvar.json?bucket=file:///mypath&decoder=json` and `blob://myvar.json?bucket=file:///mypath`?decoder=json`",
      "reference": "Don't need the `, err` part since you've already handled it."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Please add two additional SECTIONs that show that this also works if the dative bond is in the reactant (reaction SMARTS `[O:1]->[H+]>>[O:1].[H+]`) or in the agents (reaction SMARTS `[O:1][H]>N->[Cu]>[O:1].[H]`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What happens if the certificate rotation fails and we are prematurely removing this file?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "does this change belong here?"
    },
    {
      "prediction": "I don't think we want to use `w.workflowDir` here, but I don't think we want to use `w.workflowDir` here, but I don't think we want to use `w.workflowDir` here.",
      "reference": "This returns an error"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If we think we might someday write a native nftables backend, do you think it would make sense to just use generic dataplane configuration? e.g, `dataplane = iptables | ebpf | nftables`, but for now selecting `nftables` uses iptables in nft compat mode?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like that helper function is general enough that it should reside in testhelpers"
    },
    {
      "prediction": "This is a hack.",
      "reference": "This isn't incorrect IMO, but I think it would be better to fix this in drupal7PostStartAction and also in drupal6PostStartAction. It seems to me like those were both somehow neglected on this. Use drupal8PostStartAction as example. Congrats on your first golang PR! Please make sure to test it manually."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd like to ensure that the error message at least has some reference to the flag that is not allowed. Something like `/ERROR(.+)--hosts/` would work."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Should we say \"specifying two public subnets\"?"
    },
    {
      "prediction": "I don't think this is necessary.",
      "reference": "Issue number? When? Why?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "You should not rely on `PitchCommand` being imported into speech. Please import it from `speech.commands`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is this a constant used in the Nessie project itself? If so, perhaps you might consider a follow up for adding `NessieCatalogProperties` class at some point, to help make them more clear to users looking to adopt Nessie coming from the Iceberg repo itself  "
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "maybe we should rename: MinTaskID -> MinTaskIDExclusive, MaxTaskID -> MaxTaskIDInclusive,"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "You may need to make this configurable if we expect people to be able to use the normal Nvidia runtime on other Linux distributions like Ubuntu or Debian."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Originally the DenyExport was a subscribe permission because it meant that if on this LN connection, if we deny export of \"foo\" it means that it would reject a subscription (hence subscribe permission) on \"foo\" from the other side. Now you are changing to simply not allowing this server to publish on \"foo\". I am not saying this is wrong, but we completely flip the meaning."
    },
    {
      "prediction": "I don't think it's a bit of a hack, but it's a bit of a hack.",
      "reference": "> k1 src0 src2 -> dst s/src2/src1/ nit: k1 is actually src0 according to instr_get_src(instr, 0) which makes this a little confusing"
    },
    {
      "prediction": "I think this is a bug in the kmd controller.",
      "reference": "I believe that you meant to have the following on the second one, right ? `dataDirStat.Mode()^0077`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The reason a `ByteCount` is used here, is that the H2 mapping in gQUIC requires this layer violation, which is why `CloseRemote` is not part of the public API. This layer violation will be resolved in IETF QUIC"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I dig the helper function!"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please add the Copyright header."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is this the best way to import `FileSystemTarget`?"
    },
    {
      "prediction": "I think this is a hack, but I don't think it's a good idea.",
      "reference": "Wait -- os_local_state_t.tid is thread_id_t though, so we need to read a pointer-sized value via READ_TLS_SLOT_IMM, rather than changing these locals to ints. Maybe have a READ_TLS_TIDSZ_SLOT_IMM or sthg."
    },
    {
      "prediction": "I don't think this is a bug in the ICorDebug interface.",
      "reference": "Don't use ! in the messages because it isn't used on xplat. There is a SOSPrefix define that can be used (blank on xplat and ! on Windows). Do we really need 3 newlines?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "print out what we got here in the error"
    },
    {
      "prediction": "I don't think this is a bug in the jx_eval_null function.",
      "reference": "Does this need to be global?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Yep, could be simplified. Now looks like other *Map.values() impls"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "This method will be for debug?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "// Key returns the private key for a specified name that was encrypted with the // provided password. If the private key does not exists it creates a new one // with a name and the password, and returns with `created` set to true."
    },
    {
      "prediction": "I don't think this is a class, but it's not a class.",
      "reference": "Adding the type hints revealed that it was necessary to distinguish between a ``PackageEntity`` and a ``ClassEntity``, because the ``ClassEntity`` has additional attributes that were dynamically added in the previous code, which confused ``mypy``."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "These two functions should be available now."
    },
    {
      "prediction": "I don't think this is the case where we don't know what to do with the file.",
      "reference": "`fi` is what the result of Stat is called elsewhere in this file not `finfo`"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use #replace to reorder the hash.",
      "reference": "I'm confused; are we just dropping these methods without deprecation?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "can we use PC's time to version in Distributed Systems?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `user_full_name` attribute?",
      "reference": "is this \"unless\" actually needed?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "We don't accept empty words for lookup anymore, again"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We'll have to account for CI installations being faster than local ones. Do y'all think we should leave it at < 30 green / < 50 orange | >= 50 red or lower our thresholds?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "No need for this to be `W3C_` since there is no JWP equivalent"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "As far as I can tell, there's nothing that creates an instance of `Random` or that calls `rand` or `seed`. Am I missing it? If not, let's remove the `Random` class since we don't really need it and we can move the definitions of `shuffle` into `RSpec::Core::Ordering`. One less type :)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this ever actually used?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this section of the codebase should be noted as a candidate for caching, and as a place where multiple tipsets is making things extra tricky"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Do we need to save the existing value of the stolen reg somehow?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "maxResults should come from FLAGS once #244 is submitted."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "is this wanted?"
    },
    {
      "prediction": "I don't think we want to use `pytest.importorskip('linode')` instead of `pytest.importorskip('linode')` instead of `pytest.importorskip('linode')`.",
      "reference": "What exception is actually happening here? AFAIK `pytest.importorskip` with just return `None` if there's nothing to import. Which means that this check'd always return `True`. `pytest.importorskip` is specifically designed to trigger skipping the current test anyway so I don't know why you would wrap it like this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does it send requests with urlencoded bodies anywhere? I thought it sends only json. Maybe content-type should be `application/json` by default?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I'm not sure about adding more flags here when we're trying to simplify things, I thought we were going to check for patches changes to decide if we needed to update or not?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`testExecutionPb` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `getProviderReference()` method.",
      "reference": "~Method is public and removing it would be a BC Break, you can deprecate it if you want.~"
    },
    {
      "prediction": "I think this is a bug in the interpreter.",
      "reference": "this got me a little confused when reading `build.log`. The err is printed with a log.Error later on but that ends up after the stack trace."
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we make these more explicitly for Rust only? It seems like JS and Go use flags with their name in them."
    },
    {
      "prediction": "I don't think this is a good idea to use `mungeURLPath(u.Path, os.PathSeparator)` instead of `mungeURLPath(u.Path, os.PathSeparator)` and `mungeURLPath(u.Path, os.PathSeparator)` instead of `mungeURLPath(u.Path, os.PathSeparator)` instead of `mungeURLPath(u.Path, os.PathSeparator)` instead of `os.Path",
      "reference": "Should unsupported query parameters just be ignored? I think that's more common than error out."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Actually can we avoid mentioning `Register._UNSET_NAMESPACE`. I thought of it as an implementation detail of the simpler concept of \"being unset\". Perhaps the docs become more natural if we remove the \"If called without arguments or with ...\" part and just say \"you have to call this function without arguments at the end of any file it has been used. That is to ensure blah blah\". Something like that. Just a suggestion."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I assume it raises COMError? If so perhaps best to just catch that specifically, so as to not hide other more critical errors."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Since minify can generate errors, it should at least go after the errors middleware. And you definitely don't want to be minifying after the gzip writer has closed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: we could remove the `config` field as it is a duplicate of the `provider.config` field."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Nit: from the Internet."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `go-ethereum-hdwallet` package.",
      "reference": "this is internal package, move to bottom and run 'make fmt'"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why is this better than ApplicationStopping?"
    },
    {
      "prediction": "I don't think this is the default type of ACME challenge.",
      "reference": "Maybe worth expanding that these 2 are supported by cert-manager but other values exist"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why was this merged? It should have raised some questions IMO @core23 @OskarStark . It's already in 3 releases now, so we can't revert it can we? How can we fix this? Please have a look at #1065"
    },
    {
      "prediction": "I think this is a bug in BesuNodeRunner.",
      "reference": "What if `node.jsonRpcConfiguration().getAuthenticationPublicKeyFile()` is empty string, would that cause a problem here?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The `omitempty` struct tag does not do anything for non-pointer structs. I think we may need to consider making both of these fields pointers, so that they are excluded from output when not set, and also to make it easier to compare to the zero value. That said, I'm happy to merge this now and open an issue to verify the behaviour is as we want ahead of cutting v0.6.0."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think this is should absolutely be `==`, as the interface cannot control the implementation of equals (and it's part of the contract of the enclosing function). Can we add this interface to the exceptions of the rule?"
    },
    {
      "prediction": "I don't know how to handle this, but I don't know how to handle this.",
      "reference": "It looks like the UID is the only other thing that we use from `namespace`, so I suggest to copy that out and lose `namespace`, so we don't have to worry about setting it to nil."
    },
    {
      "prediction": "I don't think this is a bit of a hack.",
      "reference": "Can we define this constant in the`deploy` pkg instead? this would allow us to keep it private"
    },
    {
      "prediction": "This is a hack.",
      "reference": "I don't like this fixture name, should be a noun like `initialized_linter` ? But it's outside of the scope of this MR."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Could we keep this as a static reference (JsonPrinter.jsonAsDatasetDto(releasedVersion); and perhaps change the constructor line to just be a static set method and use that here instead? (I suspect it was the warning that 'static methods should be accessed in a static manner' from my IDE that caused me to make this change in the first place...) (I can make a PR to your branch if you want.)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Keys.COMMAND seems to be an alias to Keys.META. That isn't mentioned?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should go in `ConfigLocal` (and then re-generate the mocks)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nitty but entry.get for the same thing"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `init` command.",
      "reference": "Might not hurt to mention the function never returns (since this all ends in `execve`) so `main` never actually runs."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "nit: add new line after this block"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I believe there is some javascript that also uses this 60px number for calculations. I think I'd rather keep the number in px instead of rem to make that correspondence easier to see. If 3.25rem != 60px, can you also change the other place where `60` is used to in the JS?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "retrying is an installed 3rd party library just like jinja and sendgrid; perhaps try grouping all of them together?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "you could always use List.listIterator with previous() and hasPrevious() to traverse all kinds of j.u.List backwards. No need for special cases for ArrayList and Vector."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "remove the bitmap of index 1 from the list not the 0th one. because when we keep on undoing, it would be better if we end up with the original image rather than some randomly edited image. I am not sure whether only just removing bitmap from the list would clear memory. I think you should call bitmap.recycle before removing that bitmap from the list."
    },
    {
      "prediction": "I don't think the License is included in this file.",
      "reference": "this is a existing file so let's keep 2019"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can you change this instead to just `type.toString()` and then you wouldn't have to expose the getBitMask in the enum. (Alternatively you could have used `type.hashCode()` but that doesn't feel as nice)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "AsReadOnly() would be better here"
    },
    {
      "prediction": "If `changes.partial_sync` is enabled, `partial_sync` is added.",
      "reference": "I suggest that we use `query_based_sync` instead of `partial_sync`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "How does the user use this? By converting the type using `As` function and add the header? Maybe add an example on how."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'm trying to understand the effects of this change. Is setting this to something other than the old default (that is, `initCodeTransformer = new InitCodeTransformer()`) generally necessary, or are we doing this only to support Python?"
    },
    {
      "prediction": "I don't think it's a field, but it's not a field.",
      "reference": "\"Constructor\" isn't a standard term in Go or this project, although we use it informally amongst ourselves. And I think it will confuse people coming from languages like Java. So can we leave this as it was?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why do we have to change the test dir?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This should test the flattened tree instead. details > summary works across shadow tree boundaries."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Not sure I am a big fan of these duplicated Log classes."
    },
    {
      "prediction": "I'm not sure if this is a problem, but I'm not sure if this is a problem.",
      "reference": "It's long-winded, but the convention is to give constants a common prefix which, see `reasonDomainVerified` ."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "Using lanes later down, this threshold could be reduced for similar effects. Otherwise we look a bit to far."
    },
    {
      "prediction": "I think this is a bug in conda-pack.",
      "reference": "Let's get more verbose about names. struct `wq_conda_environment`: if it can really only be used for conda. struct `wq_software_environment`: if it has potential use outside of conda."
    },
    {
      "prediction": "I think this should not be needed.",
      "reference": "Should we set this back to `false` inside each `t.Run`? so that we can have more than one testcase that can have paginated responses"
    },
    {
      "prediction": "I don't think this is the case for the `deleteManifests` property, but it's not the case for the `deleteManifests` property, but it's not the case for the `dataManifests` property, but it's not the case for the `deleteManifests` property.",
      "reference": "What about using `dataManifests == null || deleteManifests == null`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The `HitsThresholdChecker` should be created once and shared within the collectors ? We also don't need to use the `GlobalHitsThresholdChecker` if the executor is null or if there is a single slice."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `k8s.io/apimachinery/pkg/util/intstr`?",
      "reference": "move this to below `antrea.io` import section"
    },
    {
      "prediction": "I think this is a bug in OpenTelemetry.Trace.",
      "reference": "Seems likely to confuse people. What if we moved it into ActivitySourceAdapter and made it private?"
    },
    {
      "prediction": "I think this is a bug in the future. I think this is a bug in the future.",
      "reference": "gas price don't need to be a multiple cuz we support allll gas prices now"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We are exposing implementation details in the interface. What if there is no processes involved in an implementation of `ITestRequestSender`?"
    },
    {
      "prediction": "I don't think this is a problem with the server side.",
      "reference": "It would be awesome not to handle the broad exception here. Instead, raise a custom exception, something like `ModelNotSetException`, from the `require_model()`, and then handle it here with a nicer message to tell the user to set the model first."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This already exists under the `theme` lang key, please remove this."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Let's add a simple inline HOC around the default export below to provide the value as a prop (no need to introduce a reusable function for this yet)."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "I believe that you end up printing out the result of the assignment here instead of the netmask."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We have to update the filename here."
    },
    {
      "prediction": "I don't think this is the default behavior.",
      "reference": "The `--cpp-field-case` looks like `--cpp-field-style` instead of `-case`. - 'unchanged' - leave unchanged (default); - 'upper_camel' -upper camel case; - 'lower_camel' - lower camel case."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I haven't thought about this a lot yet, but if we were to try this change, we'd still need to keep the code to delete it from the `.origin` file for backcompat."
    },
    {
      "prediction": "I don't know how to import this, but I don't know how to import it.",
      "reference": "In my opinion I think it is possible to add `private final` here"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Feel like \"exit\" doesn't convey that the packet will be dropped. \"drop-and-exit\" or \"error-exit\" maybe?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "How do you feel about \"The Main actor\" instead of \"A Main actor\", while we're already here changing the message?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I cannot see that this new permission is used anywhere? And if the new zk handler is covered by `zk-read`, should not also existing `ZookeeperInfoHandler` handler implement PermissionNameProvider and declare the same permission, for consistency?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Is this reasonable?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We may move this TODO to Line15."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "You have to verify the return type. If it's a reponse, return it. Otherwise do nothing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "No. Keep the header include and do `extern template ...` to skip the instantiation from that compile unit. (I pushed a fix directly to your branch)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "these tests are currently somewhat nonsensical. This code expands to `a, b = {}.keys` when it really should be expanding to `a, b = {}.keys()` -- though fixing this causes the test to fail so I suspect something worse is going on here that I don't quite understand?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Why did this need to change?"
    },
    {
      "prediction": "I think this is a bug in IoTeX.",
      "reference": "/go/pkg/mod/golang.org/x/xerrors@v0.0.0-20190410155217-1f06c39b4373/adaptor_go1_13.go:16:21: Frame not declared by package errors (from `typecheck`)"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's a string, but it's not a string, but it's not a string.",
      "reference": "Probably doesn't go here because I think it's specific to the HTTP API layer. This class is too internal to declare such a name."
    },
    {
      "prediction": "I think this should be the same as the check.body().string().isEqualTo(c.body().string()).isEqualTo(c.body().string()).isEqualTo(c.body().string()).isEqualTo(c.body().string()).isEqualTo(c.body().string()).isEqualTo(c.body().string()).isEqualTo(c.body().string()).isEqualTo(c.",
      "reference": "in preparation of directly writing the /health endpoint one day.. we should have content checks."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "question (non-blocking): Is there a benefit from using `%q` instead of `%s`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I would suggest to keep two empty lines between functions in cpp files"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change causes the test to fail on both rocm-1.9.x and rocm-head."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'd consider moving all fix related stuff to a distinct package to avoid contaminating the base package"
    },
    {
      "prediction": "I'm not sure if it is a directory.",
      "reference": "Use `os.path.join` for path concatenation."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Use upper case: YOLACTHead, YOLACTProtonet, YOLACTSegmHead"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The driver tests should be updated to use the concrete type instead of the driver directly; right now your test coverage of the concrete type is 0%."
    },
    {
      "prediction": "I think this should be a better way to do this?",
      "reference": "I would prefer the message to be more actionable. Like 'There should be no space between & and the variable name' or something similar."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The image attribute is not supposed to be the text of the node. I'd rather keep it separate (the previous `@Text` attribute was fine). A practical reason for that is in the future, other languages may have a way to get the text of their node, in which case that wouldn't be fetched with `getImage`, for compatibility, but probably with a `getText` method, or `getSourceCode` like in #1728. Also we *may* deprecate or otherwise put `getImage` out of use as soon as 7.0, given its contract is super loose."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The `[] +` seems weird to me. Why is it there?"
    },
    {
      "prediction": "I don't think this is a problem with the format of the email.",
      "reference": "Not sure if this constant is defined at the right place style-wise. Maybe move it up to before 'belongs_to' like DISCOUNT_TYPES in coupon.rb?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What about a line with just spaces/tabs? Or a line with a couple spaces followed by a `#`?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "if funder_is is not blank (L375) there is not need to check if org_id is not blank (L379) since you will never enter in the if (L374)."
    },
    {
      "prediction": "I don't know why this is the target?",
      "reference": "Don't need this-> here."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I'm a little concerned about relying on a private module, as they could change the implementation at some point, I'd like to have some test to validate this is working as intended."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "There might other values that we don't support here (eg. `[]`). So it might be safer to check for the supported types instead (string or number)."
    },
    {
      "prediction": "I think this should be a function call, not a function call.",
      "reference": "FYI, It won't have any benefit to move from trivial types."
    },
    {
      "prediction": "I don't think this is the default value for the `secrets-ssm-environment-variables` property.",
      "reference": "i missed these discussions- but ` \"secrets-ssm-environment-variables\"` is what was agreed upon with cp?"
    },
    {
      "prediction": "I'm not sure why this is a bug in clutch.",
      "reference": "whats the difference between this package and `github.com/golang/protobuf` ? or did vscode just decided this was the package it wanted to used?"
    },
    {
      "prediction": "I'm not sure if this is a new instance of `AddRepositoryDialog`?",
      "reference": "Just asking: What does this line do? Does it add the stylesheet from the parent to the dialog?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Including the scikit-learn dependency here would pull in scikit-learn for everyone who depends on Dagster. If you put it in the setup.py under docs_snippets, we'd avoid that problem (although I think it's already there)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why remove this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why remove this? It seems like we should keep this around as a regression test, unless we can guarantee this will never be called without a model set (does your new code guarantee that?)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Because this defaults to `{}` if `global._googlesitekitUserData?.permissions` is `false`-y, the checks below around `state.capabilities` always result in the `!! capabilities === true` path. This shouldn't have a default value of `{}` if there's the possibility that `global._googlesitekitUserData?.permissions` can be `undefined`/`false`/`null` legitimately."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Please add a space after the comma here (generally, with arguments there's always a space after commas)."
    },
    {
      "prediction": "I'm not sure if this class is used with cautious, but I'm not sure if this class is used with cautious, but I'm not sure if it's used with cautious.",
      "reference": "From the context, should it say \"Flags defined in this class must be used with caution...\" ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We don't need this file, we can use the one that is in the grid-ui directory"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "\"Exported key for account\"?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Normally we use Environment.NewLine unless you really want it to always be \\r\\n"
    },
    {
      "prediction": "I don't think this is a problem with the `VerifyHeaders` method.",
      "reference": "why did you remove `verifyHeaders`?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Thanks for cleaning up these deprecated calls"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "@akarve this breaks error catching logic on the front end, I'll fix this. That's why I prefer to use some machine-friendly error codes that won't change frequently."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `requireRemoteQuery` function.",
      "reference": "We support process remoteQuery for Service. Why are we removing it ?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `show_exceptions=false` option.",
      "reference": "This is specifically for testing?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think this is related to the social stats and probably does not need to be removed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Yep, jsdoc again .. It seems that when the plugin description is wrapped within `eslint-disable/enable` expression it's not generated at all. After adding the `@class AutoColumnSize` tag right after the `@plugin` tag the plugin appears in the docs. Please review the other plugins."
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "This usage of the result doesn't look quite right. I would not expect the first page of values to be empty if there were multiple pages of results. This also obscures the error case when no values are returned (handled in the next `if` block) by returning a more generic error from the Azure SDK from `result.NextWithContext()`."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "unknown field AddressDetails in struct literal (from `typecheck`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just noticed, are we specifically missing the addition of `SharedConfigState: session.SharedConfigEnable` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure what this is. Bad merge?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this may be a RW lock."
    },
    {
      "prediction": "I'm not sure if this is a plugin helper.",
      "reference": "Perhaps we should tuck this away into a dedicated subdir and name it `config` or something similar? Or maybe it would be happy living in `common`?"
    },
    {
      "prediction": "I don't think we need to learn it?",
      "reference": "Doing a select query inside of a loop like this is not ideal. We should fetch recipes once and then loop through it in memory to perform this check"
    },
    {
      "prediction": "This is a hack.",
      "reference": "too long here. (104 > 100)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Use TryGetValue instead of catching exception"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think this method should be either: - a static method of `RTPSWriter` to avoid a StatelessWriter redefinition of the function. - a setter in the `CacheChange_t` struct."
    },
    {
      "prediction": "This is a hack.",
      "reference": "You add a stream back reference for trailers, and all of the sudden we have tight coupling!  "
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "I don't think we use `AspNetAmbientContext` anymore since . We can probably delete this file."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "Please avoid committing build artifacts, as they produce unnecessary conflicts and noise."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is vendored code so i would hesitate to make random changes to it"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We are using a different style for JSON tags. `ethAddress` - camalCase `referral_code` - snake_case"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Should this be `\"Microsoft.AspNetCore.Http.DefaultHttpContext\"`?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "removed asserts from `Vector` as it's stable enough and it may hinder inlining, even if turned off :/"
    },
    {
      "prediction": "I don't think this is a problem with the `get_message_definitions` method.",
      "reference": "Do we want to raise on the function or on the decorator?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `additional_info` field.",
      "reference": "How complex is to to replace `album_*` with `release_*` everywhere in the `Listen` class and places that use it?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You haven't changed any of the callers of `.Add` to check the return value, so we're now ignoring duplicates. Please fix that."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `isHiddenWithCSS` method, but it's not the right thing to do with the `isHiddenWithCSS` method.",
      "reference": "@straker should this not push to `vnode._cache.isHiddenWithCSS`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "\"an interface\" in conceptual sense vs \"interfaces\" or \"set of interfaces\", referring to the Go interfaces - database/sql uses the latter, should we?"
    },
    {
      "prediction": "I think this is a problem?",
      "reference": "This now checks nearly all errors that can occur. How about explicitly listing cases where we want it to retry? I think there are not many cases where we want that, as the many added conditions in the last years show :)"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "Can you make this accept an action instead?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Tab inconsistency here (3 spaces instead of 2 spaces)"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but I think it's a string, but I think it's a string, but I think it's a string, but I think it's a string, but it's not a string, but it's not a string.",
      "reference": "these change means we are changing epoch to 1 hour?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Why this is defined in the middle of imports?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Could you move this to the original position?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Is there a test that'd have caught this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "ListWorkflowExecutionsRequest <- this can be nil?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Do we need to continue to support the old link, or is it dead dead dead?"
    },
    {
      "prediction": "Should we remove this?",
      "reference": "Do we need `ConcurrentDictionary`? `Dictionary` can be safely read from multiple threads. See `GlobalTags`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this seems like more of a Debugf statement"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We're capturing cb_state non-const, but the function is const so, safe enough, but after going to reader/writer locks we're all going to have to key a careful eye on anything in this pattern."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Probably want to wrap the endpoint discovery work that follows in this `if` statement instead of returning early. This will make it easier to add additional request code generation logic in the future. e.g. if we add any code generation after the endpoint discovery block this check will cause it to be skipped."
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "This test was giving a false positive because my change caused it to throw a different error that contained `createElement` when it should've been throwing this error. Caught this by looking at the code coverage and noticing that the line under the condition I changed was no longer covered lol."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this is added to wrong file. You wanted to add to cmd/agent/, right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Each `ExpectedCondition` implements `java.util.Function` These are expected to be stateless. This condition will leak previous `elementText` on the second usage, which doesn't seem ideal."
    },
    {
      "prediction": "I don't think this is a good idea to do with the `json:\"deviceID\"` type string `json:\"deviceID\"` type string `json:\"deviceID\"` type string `json:\"deviceID\"` `json:\"deviceID\"` `json:\"deviceID\"` `json:\"deviceID\"` `json:\"deviceID\"` `json:\"deviceID\"` `json:\"deviceID\"` `json:\"deviceID\"` `json:\"deviceID\"` `json:\"deviceID\"` //",
      "reference": "Could we consider a more explicit name, like `devicePciAddress`?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Why change this from a foreach? I can't see it gaining anything here and code styles shouldn't change just for the sake of it."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string.",
      "reference": "Is this supposed to be part of this PR?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `getHasListItem` or `getIsHidden`?",
      "reference": "DRY, worth extracting this method to axe.utils"
    },
    {
      "prediction": "I don't think this is the default.",
      "reference": "I think there's another spot for this in DefaultCapabilityMatcher"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "`QtOSError` inherits `OSError`, so I don't think it's needed to list them both here."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Instead of patching vendor, let's update the version of sdk-go to a more recent one that doesn't have this line."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Don't think this should be here. The default is set somewhere else."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not really important in this PR, but does BlazeMeter describe \"progress\" values anywhere? It might be nice to have a set of constants like `PROGRESS_DOWNLOADING_IMAGE`, `PROGRESS_BOOTING`, `PROGRESS_RUNNING_TEST`, etc in our BZA client."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "nit: `<p>` after the line"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should we include the files with otf extension here, too? If not, I wonder why we do allow them in the source but we don't include them as per the setup"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i think it's OK to leave this?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Does this need to be public? The only reference to `FlinkTypeVisitor` that I see in this PR is here, so I'm not sure why this is needed."
    },
    {
      "prediction": "I don't think this is the right thing to do with the NVDA menu.",
      "reference": "No line at end of file warning"
    },
    {
      "prediction": "I don't think this is a class, but I don't think this is a class, but I don't think it's a class, but I don't think it's a class.",
      "reference": "This looks unused, shouldn't it point to inner processor in any way?"
    },
    {
      "prediction": "I don't think this is the case for the first N node, but it's not the case for the first N node.",
      "reference": "There may be a few isolated cases where the FirstN node is added during preCodeGen. Please see GenPreCode.cpp RelRoot::preCodeGen(). The example given there about Order by where sort is added in optimizer, or a FirstN where the N value is to be specified with a param seem to be cases where we would add the FirstN later. Will current change cause such views to marked as updateable? This is minor and could be resolved later, if any change is necessary."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "I think you should compose the %sClient part using the Name class, and then do the remaining composition with plain concatenation. Side question: why does the return type name look like it is a client type name?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "All stories in this file also need the default padding."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Curious - what would be the actual value?  "
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "Is it necessary to record the palette in the checkpoint? Any reason?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Not sure how to best do this without creating a new connection to the server everytime. Do this in another thread?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "should we have a similar test for gsa18f procurements?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "change `v.recipient` to address.Address, so can use `AccountState(v,recipient)`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Open to doing away with this altogether and maybe injecting this logic somehow into `requires_approval_notice?` in LinearDispatcher."
    },
    {
      "prediction": "This is a hack.",
      "reference": "remove this and always enable tracer, just set the default timeout to something higher (20 seconds)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Can we give this field a more descriptive name? When I use a variable named `icon` I normally expect an `Image` object."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can't these just use the global `include` and `exclude` flags?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this still necessary?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Interesting! Happen to catch an exception message or anything I can look into?"
    },
    {
      "prediction": "I don't think this is a `Promise` object.",
      "reference": "did this get moved to mpromise? I don't recall if it's in that lib or not."
    },
    {
      "prediction": "I think this is a bug in Wireguard.",
      "reference": "json objects should be `camelCase`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "QuarterGiBSectorSize? SectorSize265MiB? Spelling out 256 seems overly verbose."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe with this change we can remove `using OpenTelemetry.Logs`."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Fix this name too."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "why this is an issue?"
    },
    {
      "prediction": "I think this is not a valid class name. I think this is not a valid class name.",
      "reference": "The condition should be inverse?"
    },
    {
      "prediction": "I don't know how to use this class, but it's not a good idea, but it's not a good idea to use it.",
      "reference": "this seems to be a property key name, so should it be a inside configurationkey.java?"
    },
    {
      "prediction": "I don't think this is a problem with the `zfs` command, so we can't use `zfs` command.",
      "reference": "G204: Subprocess launching should be audited (from `gosec`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please add docs here. And also warn users that this mode should be avoided whenever possible, because any blocking IO will make the keep-alive-thread not run."
    },
    {
      "prediction": "This is a hack.",
      "reference": "We shouldn't require dimension values to be a string. They just need to be scalar values (probably we could check whether it's either a string or a number). Something more important to cover in the validation here though is to ensure that a map of `dimensionName => dimensionValue` is passed. The keys here actually need to be strings. For example someone shouldn't be able to pass an array of values."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `yarpc.Router` and `yarpc.UnaryTransportHandler` and `yarpc.UnaryTransportHandler`.",
      "reference": "let's do a pointer cast of nil, similar to the `MapRouter` above"
    },
    {
      "prediction": "I don't think this is the right thing to do here, but I don't think it's the right thing to do here.",
      "reference": "action should use a prefix of `hfg` rather than `neve` as we plan to bootstrap this as a standalone library. Moreover, previously filter/actions used in this library was using the same pattern."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I'm halfway tempted to disable this for all https connections. Do you know of any clients that actually renegotiate for any reason?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "shouldn't **call** return a boolean?"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "I don't think you need the blank import here. This one uses awsdynamodb directly."
    },
    {
      "prediction": "I think this should be a list, but it's not a list, but it's not a list.",
      "reference": "I think this should be initialized to `null` instead of a predicate. There is no need to run an extra predicate (with an extra method dispatch for each row in a data file. That's a tight loop so we should do more work here to avoid it. Instead of using `isDeleted.or`, this should test whether `isDeleted` is `null` and either initialize `isDeleted` or call `isDeleted.or`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is this and the next entry in config_handler used for?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "will your editor integrate `gofmt`, `goimports`, etc...?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "looks like the code is not properly formatted. for example here are some missing spaces in **if** command. please take care and reformat the code using default android formatting."
    },
    {
      "prediction": "I don't think this is the right thing to do with `--bug-path-length` and `--minimum-bug-path-length` and `--maximum-bug-path-length`.",
      "reference": "Please add some valid examples to help message like `\"4:10\"`, `\"4:\"`, `\":10\"`"
    },
    {
      "prediction": "I'm not sure if it's a symbol, but I'm not sure if it's a symbol.",
      "reference": "Is it only Symbols we're worried about converting? Is it not safe to just call `to_s` anyway?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `time.Second` or `time.Millisecond`?",
      "reference": "Note for those who come across this later: It was moved to `testhelpers.mining.go` so that `testhelpers.NewDaemon` and the `mining/worker_test.go` can share it."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `incomplete_trails?` or `in_progress?`?",
      "reference": "What about `sort_by(&:in_progress?)`? Maybe with a `.reverse` thrown in?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Flag is removed because it is only gRPC now."
    },
    {
      "prediction": "This is a hack to fix the problem with the `ansible-galaxy init` command in the `molecule init` command.",
      "reference": "Might be better to rephrase to: Please refer to the ``init scenario`` command in order to generate a custom ``molecule`` scenario. Since you aren't customizing the default scenario since it already exists, right?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Shall we merge these `if` for `path lib` and then do the `attrname` one. I'm trying to count `if`-calls and its getting late but I think we can reduce the number checks needed to get into L648 from 3 to 2 if you understand what I mean  "
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "why depend on recovery???"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "the done channel only aims to be closed, so `chan struct{}` is better then `chan interface{}`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you mean to have gas_oracle changes in this PR?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Is this effectively requiring browsers support javascript?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Lowercase `boolean` - use the primitive type."
    },
    {
      "prediction": "I don't think this is the case for the `checkIfBlobExists` method.",
      "reference": "This isn't the correct logic. if allowOverride == true and !blobExists then upload. Just don't do the exist check if allowOverride is set to true."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Can you replace these by `else if` please?"
    },
    {
      "prediction": "I'm not sure why this should be done here, but I'm not sure why this should be done here.",
      "reference": "Would be nice if the field had a unique class name that could be used to target it, instead of `fromRange`   But doesn't seem to be a common thing in the code base."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this code fit on one line under 80 characters? It would be more consistent with our existing style."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Not a requirement here. But i see a change in naming convention. We can rename the function to `CstorSparsePoolArtifactsFor070`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why do you configure the UART like this? It's already configured by default."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Wow. Good catch. \"This `#include` was brought to you by the department of redundancy department.\" ;)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Well it's actually calling `AuthorizeOrder` and this seems like a DebugLevel message to me, maybe it should be dropped entirely."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Should this be using the `CUDA_SAFE_CALL` macro here?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `Console.WriteLine` method.",
      "reference": "What cases do you see as being valid for not having any tests to run? If a test project doesn't have any tests to run we should avoid running it at the project level."
    },
    {
      "prediction": "This is a hack.",
      "reference": "and is it possible that mset.mirror.msgs be nil? because if so, then you would get a panic also because of that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`next->opaque` should not be cleared."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "already what? I know what, but seems like smth. is missing in this sentence"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can you put spaces after the `{`and before the `}`"
    },
    {
      "prediction": "I don't think this is the default log format.",
      "reference": "We said we would put `[ ]` around the version. `[forseti-security] [v2.3.0]`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Seems len(cnb[0]) will be the length after the write since of the *v thing we saw no?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can we make use of storagepoolclaim type rather than the generic interface{} type?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this should happen before the `go k.manage()`, otherwise the node will always try the bootnodes first"
    },
    {
      "prediction": "I'm not sure if this is a string, but it's not a string, but it's not a string.",
      "reference": "Is this actually a lint related change?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure if this is a string type, but it's not a string type.",
      "reference": "what does this do that str_param does not?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "For GCP we included the API name (see below) so you can distinguish between uses other than `blob` once they exist, WDYT?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "what would you think about doing this include on-demand within S3ObjectStore methods and then failing in a loud way?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "May be better make `stopped` atomic, then it can be just `for (auto i (node.store.latest_begin (transaction_a, next_frontier_account)), n (node.store.latest_end ()); i != n && && !stopped && elections_count < max_elections; ++i)`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "In `src/storage/InternalStorageServiceHandler.h ` file, the client in `client->future_chainAddEdges ` should be InterStorageServiceAsyncClient?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "`go.sum` needs to be updated for this. Please run `go mod tidy`"
    },
    {
      "prediction": "I don't think this is the case where the secret backend is used as the secret backend, but the secret backend is used as the secret backend.",
      "reference": "Not sure if this was discussed previously, but is there a specific use case in mind for having this as an API field rather than a configuration option on the controller manager? Is there a specific use case in mind where one would want to choose different backends for individual Clusters/Machines vs having it a global configuration for an instance of the infrastructure provider?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same thing with the OtlpExporter"
    },
    {
      "prediction": "I think this is a bug in jx_print_subexpr.",
      "reference": "Should not be removed."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `Beaker::InstallUtils::PuppetUtils` instead of `Beaker::InstallUtils::EZBakeUtils` instead of `Beaker::InstallUtils::ModuleUtils`",
      "reference": "Not a blocker for anything, but should this be moved to beaker-pe? Is that ticketed anywhere?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "this shouldn't be beforeClickOn, but rather beforeSubmit? and added to WebDriverEventListener. Since submit does not synthesize the 'click' events, this isn't accurate."
    },
    {
      "prediction": "I think this is the same as `self.currently_awaiting_approvers.first.email_address` but it's the same as `self.currently_awaiting_approvers.first.email_address`.",
      "reference": "this ternary operator is hiding an `if/else` within an `if/else` - any chance we could move the logic ELSEwhere? (see what I did there -- ?? :100: )"
    },
    {
      "prediction": "I'm not sure if this is a class, but I'm not sure if this is a class, but I'm not sure if this is a class, but I'm not sure if this is a class.",
      "reference": "Is this really internal? Or will the API be different in PMD 7.0.0? Well, the interface doesn't offer much functionality anyway..."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `datatype` parameter.",
      "reference": "Does it have to be arrays? Isn't it ragged 'data' (i.e multiple elements of different lengths)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Per my understanding, this flag only impacts \"NoCleanup\" disk. If so, we may name it more clear. The reason of this ask is because I plan to add some other flag to force cleanup for other non-NoCleanup disks."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "In my changes for `RequiresDistributionAndOrdering`, this class went away and is replaced by an inner class. I think that pattern worked well. Maybe we could do that before this one to reduce the number of changes here."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Shouldn't this be called `hp` instead of `life`?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "Because the default value of allowedOrigins is * (all origins), so it isn't necessary to set again at all."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Undo this modification"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please check my thoughts here... I changed the test to not `ToString()` attribute values. This was important to test things when `net.peer.port` was both an int or a string, but I was unsure if Zipkin supported non-string attributes."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Looks like you made changes on `CameraResultType` class, but didn't commit them. And you also have to do the changes on the types in @capacitor/core"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you explain the history of the bug a bit, and why this fixes it?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "What do you think about `mentor_mail_to` or `mentor_mail_to_link` in order to match Rails' `mail_to` method, which is what this calls? I'm not sure about this suggestion..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like this will make the check in every loop. Consider extracting the null check."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe `it \"can safely be reset when there are not yet any shared example groups\"`? That's the edge case that wasn't working, right?"
    },
    {
      "prediction": "I'm not sure why this is a problem? I'm not sure why this is a problem?",
      "reference": "naming: please use `asmfactory`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "FYI you could use a raw string for this which removes the need for escaping the inner quotes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "2 blank lines here (between functions)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: we try to avoid whitespace changes because they can easily cause unnecessary commit conflicts."
    },
    {
      "prediction": "I'm not sure if this is a class reference. I'm not sure if this is a class reference.",
      "reference": "As mentioned below, I'm not sure why this is only allowing refs that are tagged with `*` at the start!"
    },
    {
      "prediction": "I think this is the same as the original, but I think it's the same as the original, but I think it's the same as the original, but I think it's the same as the original, but I think it's the same as the original, but I think it's the same as the original, but I think it's the same as the original, but I think it's the same as the original, but I think it's the same as the original.",
      "reference": "Don't forget the {} symbols, and please use EqualsBuilder and HashcodeBuilder as possible"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Allocate buffer once outside loop."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It would be better to check that system.nodes[1]->network.port is somewhere in the target without specifying its exact position. But it is a very minor point and I have no string opinion on it just thought I'd mention it because our tests in general have too implementation detail."
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "Should this be in a bundle?"
    },
    {
      "prediction": "I don't think this should be necessary.",
      "reference": "When Activity is lost (more precisely, ExecutionContext is lost) in the HttpModule we restore the root (HttpIn) Activity. That makes this assert invalid. I tried to fix the HttpModule so that it restores the Activity that was last running, but it is impossible to retrieve do to the way ExecutionContext works. It isn't an issue to remove the assert, but it is unnerving. Any instrumentation running in IIS reliant on Activity.Current could run into trouble."
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a better way to do this.",
      "reference": "what was the point in moving handlers registration into a separate method?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "At this point we probably want to ensure there's a store command set."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `isHardened` flag. I don't think this is the right thing to do with the `isHardened` flag. I don't think this is the right thing to do with the `isHardened` flag. I don't think this is the right thing to do with the `isHardened` flag.",
      "reference": "This code is way too complicated for what it does. I don't want to be a PITA, but what can you consider rewriting it in a simpler way? I'm talking about the whole `_getDerivationIndexes` function"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Don't throw base exception, specify more precise type"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Recursive -> Recursively converted -> convert"
    },
    {
      "prediction": "I don't think this is the case where we need to check for `generate_object_based_api` and `generate_object_based_api` and `generate_object_based_api` is true, but we need to check for `generate_object_based_api` and `generate_object_based_api` and `generate_object_based_api` and `generate_object_based_api` and `generate_object_based_api` here.",
      "reference": "why is this object API only? I think the reason why we didn't do this before was because this code was shared with Java which doesn't have value structs."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "just to confirm, so backend will deal with both old format and new format?"
    },
    {
      "prediction": "I don't think this is a bug in Datadog, but I don't think it's a bug in Datadog.",
      "reference": "huh, look at that, I wasn't aware you could constrain a type by Enum"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Even though the debug parameter is effectively ignored, should this default to `false` instead of `true`?"
    },
    {
      "prediction": "The \"License\" is distributed on an \"AS IS\" BASIS.",
      "reference": "What is the purpose of this interface? Unlike ParamDocView, it doesn't seem to be used anywhere to enable polymorphism"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "We added a library to generate a UUID for the request_id directive \"github.com/nu7hatch/gouuid\" can we uses the same one for what you want rather than add another dependency? Or if the google one is better can we remove the nu7hatch library?"
    },
    {
      "prediction": "I don't think this is a bug in the net.UDPConn.SetTTL method.",
      "reference": "Shouldn't this be `i * Interval`? You're multiplying nanos with a Duration, I'm not sure what's the result :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I guess it's not no-access to match Windows where guard pages are readable."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Not a blocker, but would probably be useful to have a `scope :non_pending_approvers` on the `Proposal` model."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `TaskProcess` class.",
      "reference": "Add trailing comma"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I see someone say SIGKILL can not be caught by process. The original code here about `SIGKILL` is useless?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "As it is a mobile only theme, please make sure the option appears only on mobile"
    },
    {
      "prediction": "I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string.",
      "reference": "Would like a docstring and type annotations here"
    },
    {
      "prediction": "I don't think this is a problem with the `shard_key_fields` property.",
      "reference": "This is an API change. Why was it made?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please move using inside namespace."
    },
    {
      "prediction": "I think this is a bug in Nethermind.Blockchain.",
      "reference": "shall we create some enum flags for setasmain shouldprocess and pos?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Should this `PUPPET_AGENT_STARTUP_MODE` have a corresponding yardoc change?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the test_yankpaste_bdd.",
      "reference": "Why not simply remove the `pytest` import now that it's not needed anymore? :wink:"
    },
    {
      "prediction": "This file is part of the test code.",
      "reference": "Yeah, not filled in yet."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "don't use style. Use a class instead. reducing `col-xs-12` down to 8 or 6 or whatever should do the trick"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "should we also do `reloadCache` when database is null?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why not just return QueryMol directly? Why require the copy?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Could you add a docstring?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "looks like you added newlines after blocks in a few files - I generally like newlines before/after multi-line blocks _except_ when the end the block is directly nested inside another block (eg: two `end`s next to each other) what do you think?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "@jlerbsc 's fix in #2918 in action - thanks! :smiling_face_with_three_hearts:"
    },
    {
      "prediction": "This is a hack.",
      "reference": "nitpick: Please lower-case `Zero_count` (as it's a literal argument name) and `Argument` here."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "change the name of the function to match its functionality? account IsIssuing?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "for later: add docstring (can just copy paste Pandas')"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `require` and `require` instead of `require` and `require` instead of `require` and `require`",
      "reference": "nit: @sonofachamp pointed out to me that the idiomatic way is \"archermocks\" (lowercase for package names)"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Ugh I'm stupid, can you change this to `yarpc.InternalErrorf`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We instantiate some metadata tables in tests so I kept the old constructor too. Won't harm if someone is using it directly too."
    },
    {
      "prediction": "I think `perDocumentLimit` is not used in `limit` and `perDocumentLimit`?",
      "reference": "I think the better place to put this might be `lib/options/PopulateOptions.js`. That should make it easier - checking options in `populate()` can get confusing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Lets have simple function arguments here, because now struct `traversal.Params` started to have 2 purposes: 1. used as contract in DTO between consumer-provider 2. as function parameters for internal code calls"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Probably best not to have an empty test...."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "`image_tag` in the `testimonials` files?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I believe flow.toObject() method is throwing NPE if SLA option list (i.e. this.executionOptions.getSlaOptions()) is null or one of the value in the list (i.e. this.executionOptions.getSlaOptions()) is null. If that is the case we could fix root cause of NPE in the ExecutableFlow.toObject() method. The corresponding code to populate SLA options can be modified as follows. final List<Map<String, Object>> slaOptions = Optional.ofNullable(this.executionOptions.getSlaOptions()).orElse(Collections.emptyList()).stream() .filter(Objects::nonNull) .map(slaOption -> slaOption.toObject()) .collect(Collectors.toList());"
    },
    {
      "prediction": "I'm not sure why this is the case for the `iconImageSource` and `coverImageSource`?",
      "reference": "So I haven't tested this - but since the icon location is just directly dumped into the img _src_ attribute, won't this cause issues with Ghost blogs in a subdirectory? If I'm misunderstanding what the purpose of the default is then let me know  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why swallow the exception here rather than propagate it?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "How about `column_index_names`? `column_names` sounds ambiguous."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is the case.",
      "reference": "+1 on this. Do we want to have it as `WRITE_METRICS_MODE_COLUMN_CONF_PREFIX` to be consistent with defaults? Is there a possibility we will have `READ_METRICS_MODE_COLUMN_CONF_PREFIX`? Not sure."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shall we use different inputs for `PySpark < 2.4` where `transpose` won't work with different data types."
    },
    {
      "prediction": "I think this is a bug in pyspark.sql.types.NumericType.",
      "reference": "we should sort the headers like in spark: public packages, then pyspark, then internal"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "looks like we should drop this var from the transport options struct"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Ah, yeah, this is the test for the validation that I mentioned in a remark above about relaxing the validation."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For tensors, it is better to illustrate the shape."
    },
    {
      "prediction": "I don't think this is the case for the `google-site-kit/v1/data/` path, but it's not the case for the `google-site-kit/v1/data/` path, but it's not the case for the `google-site-kit/v1/data/` path, but it's not the case for the `google-site-kit/v1/data/` path.",
      "reference": "This was removed in a recent PR for the admin bar, but should have been kept. It's been restored in the other admin bar PR but I've added it here to for completeness."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "nit: probably swap the if condition and `if/else` and check `NETCOREAPP2_1` which looks more natural."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "for the tag, should it be `requestor_rtt` since the other is `responder_rtt`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The one sad part of this is that is will generate a lot of overhead if you loop through a vector, since it obtains the vector every time. But with the current API there is no alternative I guess, and it is better to have the option than not."
    },
    {
      "prediction": "I don't think this is the right thing to do with `go-filecoin-project/go-filecoin/types` and `go-ipfs-files`",
      "reference": "nit: there should be a newline between `types` and `go-ipfs-files`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "would be nice to have this as a parameter (Options), re: technical debt discussions"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "complete ignorance here  but is it ok to import this from `com.sun`? can it break under non-oracle JREs?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Is this some way of saying that the span is going to be sampled? I'm basing this question on the condition I saw for the `OnEnd` to be called - `mustExport := s.spanContext.IsSampled() &&  )`. Shouldn't the condition be `s.spanContext.IsSampled()` to match the condition for calling the `OnEnd`?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "just calling UpdateSnapshotInfo() should be fine"
    },
    {
      "prediction": "I don't think we want to rate limit log messages by default.",
      "reference": "Was `DefaultLogMessageRateLimit` not configurable anywhere?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Please use the `assert` instead. Same below."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Owww, I think I found a typo. `suche`"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This can happen because we could get `PhantomNodes` that are not admissible as source/target right?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Should we add a note here to file a bug if this ever happens?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "overflow is still possible, isn't it?"
    },
    {
      "prediction": "I don't think this is the default value for `fail_fast` and `fail_fast`",
      "reference": "This seems more like a personal preference, so maybe this should be in your `~/.rspec`?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "To avoid a circular import between pcapdnet and automaton"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `view_source` method. I'm not sure if this is the right thing to do with the `view_source` method. I'm not sure if this is the right thing to do with the `view_source` method.",
      "reference": "Please remove this blank line."
    },
    {
      "prediction": "This is a hack.",
      "reference": "it feels that the WorkloadIdentityCondition should be added to this Status... And if you have workload identity enabled, but not working, then you can mark that condition failed, and also Mark the ready false... not entirely sure though"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I think these got refactored to `LvlFindInChain` to better conform with the coding guidelines. I think MarkL left these in for backwards compatibility."
    },
    {
      "prediction": "I think this should be a `Series` or `Series`?",
      "reference": "It's fine for this PR, but in the future try to minimize unrelated changes."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "The library -> modules and filters -> filter path changes are breaking changes or?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Can we encapsulate this check (`os.environ.get(\"TEST_TARGET\") == \"AWS_CLOUD\"`) into a small config/util function? (and also use it in `integration/conftest.py`) (I'd generally try to avoid accessing `os.environ` directly across the codebase. I'm aware that we're already doing this in a few places, but maybe we can start pulling things out - this will also help us create more systematic config/environment abstractions as we go...)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "An `if` statement would be better here. Functions, concat and reverse are all very expensive."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`Log here: connect to default factory for goerli network <address>`"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "nits, should add `break` to avoid redundant iterations."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I think we want an exception here, there should never be a transfer to a nonexisting account."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "This code is new and not tested well. While we may drop the log level before we ship 4.0, right now this is extremely helpful to users."
    },
    {
      "prediction": "I think this should be a better solution, but I think it's a better solution?",
      "reference": "Can we make these asserts more strict/precise? I remember this test helped to spot the issue of inconsistent results on different platforms due to using `sort` instead of `stable_sort`."
    },
    {
      "prediction": "I don't think this is the case for the `run-as` option.",
      "reference": "I thought about adjusting for case here as well? For example `.rb,rb,.RB,.rb` would all map to ruby interpreter specified? Is that too much \"magic\"? Is there a sane workflow that someone would choose to map `.rb` to one interpreter and `.RB` to another?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "In this and the one below, should we assert `self != NULL` first?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Why this is needed?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "we already have .meta() so I don't think we want get_meta() for PackageEntry"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "question: can we always get the startts from dagrequest?"
    },
    {
      "prediction": "I think this should be removed in the future. I think this should be removed in the future.",
      "reference": "Nit-picking, but this can be simplified to reference `properties[ 0 ]` since that is already retrieved 2 lines above."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This technically works because we call `get_targets` before we remove the target, so it's bound to have been resolved. But I'm not sure I would like to rely on that assumption. Should we also remove it from `@unresolved_targets` to be safe?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is the case.",
      "reference": "So what happens if I try to get code on a EOA?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can't we return an empty list and then just compare the lengths? Thereby removing this `if`."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Mb change it to 'doesPassRestrictions()'? Doesn't sound enough like a boolean-returning method to me."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "TODO: in fact At when used with noncurrent time should not return a next index. only latest should.."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There are scenario's where we skip an update with a placeholder, in this case tmp returns null with render, this is not an array so we `[null]` it"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@danieldietrich, this wasn't tested so I presumed it wasn't working before either :p"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please leave two empty lines after the `use` statement"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please move this import in the 3rd group which is for external dependencies"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "So what exactly is this fixing? The unit test is passing with or without this change."
    },
    {
      "prediction": "I don't think it's a symlink, but it's a symlink, but it's not a symlink.",
      "reference": "auto targetFile = fs::FileUtils::joinPath(newPath, folly::stringPrintf(\"%019ld.wal\", it->first));"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I don't see any place that checks whether the from snapshot is an ancestor of the to snapshot. That seems like a requirement for this to work correctly to me."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Other calls to getHelpText() are wrapped in an `isset()` check. Would it make sense to be consistent, and either restore that here or remove it elsewhere?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why the change? If `output_stream` is set to something non-nil, it seems odd (and potentially wrong) to overwrite it...."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Thinking this should have an underscore."
    },
    {
      "prediction": "I think this is a problem?",
      "reference": "To accommodate the change to the method being private."
    },
    {
      "prediction": "I'm not sure why this is a collection rule?",
      "reference": "Shouldn't we traverse all definitions and apply this rule over all model definitions in the doc"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please rename this class that it ends with the suffix \"Test\" - otherwise the tests won't be executed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "As a JS file, this should also receive our standard file header."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I take it memQuotaRatio is an \"out\" parameter at line 1810? Also, why use MIN_QUOTA in both the cases of memQuota being too low and too high? Contrast this code with RelRoot::codeGen where we set MIN_QUOTA only in the too low case."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "It looks like for newpullsubscription, we have two functions. One for pullsubscription with default, one for pullsubscription without default. If you remove setdefault here, then there is no differences between these two functions."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "not dramatic, but why 32bits if we allow a range that is smaller than 8?"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "- Use type from `service_discovery/dto/price.go` - Rename `Price` -> `Money`"
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "one space missing at the beginning"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I worry that having `Platform` as `string` instead of `*string` would result in it getting overriden with `\"\"` if the environment manifest config doesn't specify `platform`   . If it gets overridden as `\"\"`, that could be a problem for users that are not using `linux/amd64` right? If this indeed is a potential impact, could we double check in `ApplyEnv`'s unit test? Same with the `Platform` in `TaskConfig`. Sorry for not seeing this in my previous review!!!  "
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `connect.test.options.port` or `connect.test.options.port`?",
      "reference": "I like the new directory `/api`, what is the thinking behind `/external`?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "staticcheck flags this: replace with `for k := ..`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "There's already a sleep right above"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This feels hacky, is there a better way?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we move this logic into the `boto.compat` module? Then it's just `from boto.compat import OrderedDict` instead. Also, this is introducing a new dependency. What about users on 2.6.x that don't have the OrderedDict module installed? We may need to fall back to an ordinary `dict` so that existing code in the wild does not break."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "\"Gets the JSON serialization settings.\" would be better?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The endpoint should be in plural `/files`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "??? Why do we need to have a different API in Python? Oh, wait, I see what you did. It's to fake the namespaces. Given that I don't think the namespaces are necessary, and that less of these should be exposed anyway, I think these should go."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this line is gofmt issue? @daixiang0"
    },
    {
      "prediction": "I'm not sure if this is a test.",
      "reference": "probably better to assert the values directly; technically you could pass this test with an implementation that always returned \"\" for the subrepo for example."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "line is 161 characters (from `lll`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are these changes needed?"
    },
    {
      "prediction": "I'm not sure if this is a watch key, but it's not a watch key.",
      "reference": "It seems like reducing the sensitivity would make the test failure less likely to occur, but not fix the issue?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `I18nTimestampableTrait`?",
      "reference": "missing use statement for importing the full namespace"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Generally error messages in Go shouldn't start with capital letter. I see this rule is broken in many places here. Why?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "These test checks if selection coordinates don't return negative values in that edge cases. Please revert the changes and set `autoWrapCol` and `autoWrapRow` to `false` to the Handsontable instance. This change applies to the entire Core_selection.spec.js file."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would prefer flag SkipGasPricingValidation"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "could be `const &` ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The docs should also be updated with the new option."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Name is _way_ to generic for this patch to be accepted I think. Can you rename it to maybe `send_sns_notification` or something else you find suitable?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Out of the scope."
    },
    {
      "prediction": "I'm not sure if this is an array.",
      "reference": "I think we need an if block to check that if this API is really missing. We wouldn't want to override the browser's implementation."
    },
    {
      "prediction": "I don't think this is the right thing to do with `name` and `editorClass` and `editorClass.EDITOR_TYPE`.",
      "reference": "I was wondering, things like EDITOR_TYPE, VALIDATOR_TYPE, RENDERER_TYPE are not obligatory. Therefore if the custom editor will be registered with this method, `name` will be set to `undefined`. Should we handle this scenario?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This line should not be removed, as it is not the description of the package, but a copyright header."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Wouldn't it be more space efficient to make this a `byte` enum or bitfield?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Flake8 doesn't like the assignment, but non-use of `e` here. I think we can just remove the try/except here for `cursor.execute(sql)`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe add short example list: .... type body declarations, such as AnnotationMembers, Methods, Fields"
    },
    {
      "prediction": "I don't think this is a string, but it's not a string.",
      "reference": "These are really meant to be the keys in the capabilities, not the keys of values within the capabilities"
    },
    {
      "prediction": "I'm not sure if this is a real table.",
      "reference": "It is debatable whether we have to default this. I did this to avoid breaking custom implementations."
    },
    {
      "prediction": "I'm not sure if `attr_value['string'] is not None` and `attr_value['string'] is not None` and `attr_value['string'] is not None` is not required as `attr_value['string'] == value`",
      "reference": "# `attr_value['string'] is not None` probably not required as `attr_value['string'] == value` check is already being done"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "we shouldn't need the \"addon\" rename"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "These are covered by routing constraints."
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think this is a good idea.",
      "reference": "Could we use just a normal string here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`isFunction(Symbol)` triggers a `ReferenceError` if Symbol is undefined. Using `typeof Symbol === 'function'` is OK however."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is there an else clause (with a lock.unlock ()) missing here as well? If we think we do not need an else clause then lets add an else clause containing assert zero."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "do we foresee `32` ever changing? (as well as its use in error checking in `clerk.go`) if \"no\" this is fine, if \"yes\" it's probably still fine"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "you don't need to create a enum for this, java allows you to switch on a string ;) (since java 7?)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `roles` property.",
      "reference": "This should be `modelPromises.roles = this.get('store').query('role', ...` and the promise body should just `return roles;`. This is because the `model()` hook will pause for the returned promises to be resolved before continuing so when returning `RSVP.hash` you end up with a hash containing the values returned from the promises so the controller and everything else relying on the `model` object doesn't need to worry about things being async."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `role` attribute?",
      "reference": "This is basically a repeat of `main-is-top-level.js`. I suggest having these 3 checks point to the same evaluate file. You can change what element they test through the rule selector as well as the check.json options property. So you would have `main-is-top-level.json`, `banner-is-top-level.json` and `contentinfo-is-top-level.json` each point to `landmark-is-top-level.js`, and pass in a different `options` object which tells it what element you're trying to test."
    },
    {
      "prediction": "I don't think this should be used in the code, but it's not necessary to call `invokeListeners(PackageLoader.Package pkgInfo)`.",
      "reference": "Why do we need this check? setCore already handles nulls."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "good catch, thanks. This is going to make the user experience much better."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "TODO: remove this unused import"
    },
    {
      "prediction": "I think this is a bug in go-jose.",
      "reference": "Hmm leaking the library name out in the Workload API doesn't seem great. Do we want to catch these errors and return a canned \"could not parse token\" or something instead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think `-f gradlew` is better for code unity"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "Is there precedent for this config key? What other keys are similar? The others in this file start with `table.exec.iceberg`. Is there a reason for not continuing with that convention?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can we avoid no-change changes being committed - they make it harder to distinguish actual changes from code editor changes"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `identity_selector.NewHandler(nodeOptions.Directories.Keystore, \"remember.json\"), `identity_selector.NewIdentityCache(nodeOptions.Directories.Keystore, \"remember.json\"), `identity_selector.NewIdentityCache(nodeOptions.Directories.Keystore, \"remember.json\"), `identity_selector.NewIdentityCache(nodeOptions.Directories.Keystore,",
      "reference": "You dont use this dependency anymore"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Here is the test that checks that the sqlcipher in use was compiled with the right flags"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Turns out that if the hosts are not in an `array`, an `Exception` is not thrown anymore :-( It simply returns `null`. So, we need to attempt to parse a `string` outside the `catch` block for it to work."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "this test only covers the happy path. what about no acceptable rest template found?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since this is in a test, I imagine that the choice of `info` level was deliberate."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "this should probably be named somewhere if you want to reuse it."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `aws-sts-service-account-signing-key.key` in the `aws-sts-service-account-signing-key` environment variable.",
      "reference": "needs a rename to not include AWS"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Isn't sigma have `double` type?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "May be better use nano::keypair that generates ramdom value?"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "I think the more complete solution will save off a `ignoreUndefined` in the base class for the bulk operation (with a default of `false`), and use that for calculations. Was there a reason you didn't want to support the option from the operation level?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "The catch (Exception e) block that follows does an updateSync, which will get a SmartStore instance (while logging out is taking place) - and then terrible things will happen - a database gets created for the outgoing user that won't be openable by the returning user causing the app to crash at logout. This is a somewhat superficial fix - SmartStore should not return an instance for an outgoing user."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "huh does this work without a `Return`?"
    },
    {
      "prediction": "I think this is a bug in `RSpec.run_after_each` and `RSpec.run_after_each` and `RSpec.run_after_each` is a bug in `RSpec.run_after_each` and `RSpec.run_after_each` and `RSpec.run_after_each` is a bug in `RSpec.run_after_each` and `RSpec.run_after_each`",
      "reference": "Don't think we want this line, right? (Plus \"failing\" is spelled wrong)."
    },
    {
      "prediction": "I'm not sure if this is a local feed.",
      "reference": "I think it would be more clear to have local-feed-hiding all in one place (bottom of this method?). Further up the method, there already is some code that hides the website icon, for example."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why remove this one? It doesn't work yet, but we'll add it sooner or later."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why did you remove the struct tags?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Let's be neutral with tag names. Let's just have \"ReportURL\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Use an explicit time to ensure conversion is not copy-paste and wrong."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "The logic now is to look for `<account_out` if that is present return the string starting from there. If it is not present look for `<error` and return the string from there (which can produce malformed XML because you do not check if the closing tag matches). If this is also not found return an empty `<account_out/>`. This `<error>` output is also not consistent with the other two functions you mentioned. Do the other two RPCs not report an error?"
    },
    {
      "prediction": "I'm not sure why this should be a method of `Api::V1::VideosController` or `Api::V1::V1::V1::V1::V1::V1::V1::V1::V1::V1::V1`?",
      "reference": "Use nested module/class definitions instead of compact style."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you think we need to keep this in, or is it just leftover personal debugging? Seems like it wouldn't be too useful most of the time, but I don't care too much if you want to keep it."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the player despawned.",
      "reference": "showNPCs is not needed"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Docstring for public function pls"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This should use `t.Errorf` instead. You want the second part of the test to run even when the first part fails."
    },
    {
      "prediction": "H2O_USE_LIBUVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVV VVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVV",
      "reference": "Should this if block better be changed to `#if H2O_USE_LIBUV \\n #else ... #endif`? The reason I wonder is because that's the way the QUIC context is being initilaized at the beginning of this function. Though I would not expect practical difference between the two approaches, because ATM the only case where we create QUIC connections is when the protocol selector is set to non-zero, and because when it is set to non-zero `h2o_quiy_close_all_connections` becomes a no-op."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "`Object.is` is an ES6 feature of JS so I don't think we can use it here (or we have to change our browser support matrix or specify that an Object.is polyfill is pre-req of `preact/hooks`). Should we just do an `===` check in `preact/hooks` and provide a `Object.is` polyfill and version of `useReducer` in `preact/compat`?"
    },
    {
      "prediction": "I think this should be a string or an array of strings.",
      "reference": "This was a bug I picked up by using the TS interface as a guide, this seems like it was / is the intention, also is a bug in master (needs port)"
    },
    {
      "prediction": "The `withCollection` flag is not stored in the cluster state of the `withCollection` flag.",
      "reference": "It would be helpful to explicit here what this really means and assumes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`ExpectedBalances` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is another place where I'd feel more comfortable with declaring the class private. We can always make it public in the future if someone makes a case for that, but I prefer to err on the side of privateness for things like this that 99% of RSpec users won't have a reason to use."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Feels like this should be left as is and add a new createClientWithIssuers or something like that. Avoid all the \"\""
    },
    {
      "prediction": "I don't know why this is the case. I'm not sure if this is the case.",
      "reference": "Minor unrelated bug in the IDP flow where the error wasn't getting displayed as a `Toast`."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I thought we got rid of this thing?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please convert int params as well."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Fixed bug in implementation. Now I can run the validator from the VS Tools menu, double-click on an output line, and navigate to the site of the issue."
    },
    {
      "prediction": "I think this is a bug in Datadog.",
      "reference": "Can we rename this field to `HttpServerErrorCodes` or `HttpServerErrorStatuses`? It will contain a list of status _codes_, not a list of _errors_. (Personally I prefer \"codes\" over \"statuses\", but we can't change `DD_HTTP_SERVER_ERROR_CODES`.)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "would you please use: flb_utils_bool(...) here ?, that function wraps the on/off/true/false stuff."
    },
    {
      "prediction": "I'm not sure why this is a bug in Sarif.Driver.Sdk.",
      "reference": "`invocationInfoTokensToRedact: null` (I really like the convention of using a named parameter whenever the value doesn't communicate the meaning, such as for literal values.)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `async_test` and `simple_test` and `simple_test`?",
      "reference": "maybe renamed to `async_simple_test` if we consider supporting aug test later on?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So where is default_attributes now? Is it used anywhere else still? If not, can it be removed along with any tests of it?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "We could move this to the base class and remove all these changes. What do you think?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "While we're doing some translation work, could you extract this button text and the other static text from the view?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "Nit: Please fix indentation (note: Azkaban uses 2 spaces and not tabs)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change is necessary because the schema version is ignored unless a schema is specified. I think that has always been the intent."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The api/docs/release.dox changelog message is missing: maybe you planned to add it once NtAllocateVirtualMemoryEx and NtMapViewOfSectionEx support is in? I would say, add it here in the same diff that raises max_supported_os_version."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Just do: `return node.hasAttribute('aria-hidden')`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need `_processDataPoisoned`? Can the name or the id of the current process ever change? Or the machine name?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Did it not work out to wait until after containerd and kubelet are started?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the right thing to do.",
      "reference": "variable names suggestions from me: - damageboost, ITEM_PARSE_DAMAGEBOOST, \"damage boost +x%\" - healingboost, ITEM_PARSE_HEALINGBOOST, \"healing power +y%\" - managainboost, ITEM_PARSE_MANAGAINBOOST, \"mana restoration +z%\" alternatively the other names can stay, because \"increase\" convention isn't that bad, just change mana values to: - \"increasemanarestored\", ITEM_PARSE_INCREASEMANARESTORED, \"mana restoration +z%\""
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why can't this be determined by 'PARTIAL_SUCCESS' in the `status` field?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Does it make sense to generate a Exception here? Maybe yes, because it wouldn't make sense to generate a path without the id of the media right?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This should be made private."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "perhaps this is better modeled as a pkg-level var?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I don't think there is a maximum scale, neither for Hive nor for Trafodion. The only condition right now is that the scale can't exceed the precision. Example of a valid scale: DECIMAL(18,18). The maximum of 6 digits applies only to TIMESTAMP columns, where we don't support resolution below microseconds."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `UpdateProjectStaticUserRequest` and `UpdateProjectSingleSignOnRequest` and `UpdateProjectSingleSignOnResponse` functions.",
      "reference": "`ctx` is unused in UpdateProjectStaticUser"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this not the default, and why only for JS?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `project_id` and `repository_id` and `project_id` parameters.",
      "reference": "A repository has many badges so we should also add type column in scope."
    },
    {
      "prediction": "I think this should be removed.",
      "reference": "Now a hash set, so can't index into it."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@jpogran Does this seem like a reasonable way to know if we're in powershell vs. CMD or *sh?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "1.toLowerCase(Locale.US)? 2.where is accept bug fix?"
    },
    {
      "prediction": "I think this is a bug in pytest.",
      "reference": "We should still be providing something to the user in the case of a `KeyError` instead of a stack trace!?"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `_abiEncoder.Encode` instead of `_abiEncoder.Encode`?",
      "reference": "check Lukasz's fix with NonceReserving - is that not better?"
    },
    {
      "prediction": "I don't think this.sourceBlock_.setColour(colour, this.sourceBlock_.getColourSecondary(), this.sourceBlock_.getColourTertiary(), this.sourceBlock_.getColourSecondary(), this.sourceBlock_.getColourTertiary(), this.sourceBlock_.getColourTertiary(), this.sourceBlock_.getColourSecondary(), this.sourceBlock_.getColourTertiary(), this.sourceBlock_.getColourTert",
      "reference": "Would you explain why here please? E.g. from the PR description > the renderer expects to be able to use the secondary color as the fill for a shadow."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Lock needs to go to `RecoverFromDb` instead. Here it may cause deadlocks. My convention was that un-exported functions do not lock, only exported ones (with name starting with a capital letter)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "German keyboard would also be used in Austria and Switzerland, so this should have included `.at` and `.ch`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "since this makes the indexer thing really only used for a single table, now, you can put in a TODO for me to cleanup and simplify this"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's a string, but it's not a string, but it's not a string.",
      "reference": "Should we have this path passed from the Azkaban properties? If this is the standard path for nscd even outside LinkedIn, then we can keep it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could be a non-public field. `allowNoSubject`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Don't think this is quite right - think the build one also needs an `IsOriginalTarget` (c.f. code in `src/build`)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "what about adding typehints instead? I don't think we need to add docblocks for every private methods."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is it fine to pass the \"-o compression=on\" in the middle instead of at the end ?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `bundled_content` or `load_config`?",
      "reference": "Probably make them all keyword arguments."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why not just check the backdrop setting here as well for the time being? We can combine the code later but at least then it would be configurable if people like the backgrounds."
    },
    {
      "prediction": "This is a hack.",
      "reference": "why are we turning this one into a Warning?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Wouldn't it be better to use double quotes for the opening parenthesis ?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "Remove the cast"
    },
    {
      "prediction": "The \"License\" is not included in this file.",
      "reference": "What criteria do we use to bump the copyright years? An update to the module?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "should we rm line 269?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Perhaps the code at `source/core.py:564: postNvdaStartup.notify()` should be queued instead? If we are saying the loop must have started before NVDA's startup is complete, then the `postNvdaStartup` action is incorrect."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Needed this for testing locally with mail view but not used for any tests. Might be nice to have some seed scripts at some point."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "wait, if we only do this for successful status codes won't we miss a whole slew of responses? We should be checking this for all codes right?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Adding in the service yaml `library.yaml` here."
    },
    {
      "prediction": "I don't think this is the right thing to do with the context.WithValue(r.Context(), \"httpserver.RemoteUserCtxKey\", username)) and r.WithContext(context.WithValue(r.Context(), \"httpserver.RemoteUserCtxKey\", username)) and r.WithContext(context.WithValue(r.Context(), \"httpserver.RemoteUserCtxKey\", username)) and r.WithContext(context.WithValue(r.Context(), \"",
      "reference": "Why is this dereference needed?"
    },
    {
      "prediction": "I don't think it's a `readonlyNode` or `repoNode`?",
      "reference": "Might want to add that this only happens if you have write permissions to the folder."
    },
    {
      "prediction": "I think this field is set to `true` or `false`.",
      "reference": "Adding a small blurb about why someone would want to enable this flag would help clarify what it is for. Such as something about when providing a custom retry handler and how`ShouldRetry` will be handled with and without the flag enabled."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "assume the user will be able to register for a custom service name in future?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "The extra two empty lines seem unnecessary. Please review your diffs more carefully."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "What the reason to embed the Oracle?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Shouldn't this happen automatically with High Voltage?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This is changed because we need `projectId` to be printed as `$projectId` in PHP."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "This title change seems more accurate to me however not sure if this will confuse users."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Here (and on line 158 as well), would it be more efficient to use the String end_with() method? Not tested"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why are you creating a new (second) `RAMHandler` here? Is this just an oversight from deleting the previous code?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Move the line 27 to line 31 is better?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "In slack I mentioned we should only do this if the update is from some other device, to make sure our own updates don't cause issues. Maybe the revision check above is good enough to prevent this, but I just want to make sure you thought about it."
    },
    {
      "prediction": "The `--seed` option is deprecated.",
      "reference": "I would instead explain that random is the default, but you can switch back to defined, or another ordering scheme."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `screenReader` and `recursed` properties.",
      "reference": "Is there a reason you left this at 0?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The value of `key` will never be `null` at this point, because `getKey()` will generate a value if it is `null`."
    },
    {
      "prediction": "I don't think this is a bug in the code, but it's a bug in Datadog. Trace.ClrProfiler.",
      "reference": "NIT: You should first check if AdoNetExcludedTypes.Count is greater than 0 before calling Contains (fast-path)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "should rearrange so as to follow import ordering."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "what is the use case for create workflow with completed state?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Probably best not to have an empty test...."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Missing the license"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Looks like this was previously guarded by `EnableCleanupReplicationTask` flag. Now looks like this is always needed. Just want to confirm the intention is if `GlobalNamespace` is enabled then we want run cleanupReplicationTasks in all cases?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Potentially it'll be good to remove all of them excluding \"tbb/tbb.h\" But let's do it next time  "
    },
    {
      "prediction": "I think this is a hack, but it's not worth it.",
      "reference": "I would just mention which tolerance - namely as reported by ``sys.float_info``"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `limit` parameter.",
      "reference": ":+1: Ideally this'll become something you could pass in to the config"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should using `thenValue` to replace `then` ?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This follows the convention of each callback starting with the `IsIntegrationEnabled` check."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is not required to be part of this PR right? (With UpDownCounter being absent in .NET, we can make this hardcoded for now, i think)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Add the PipeFactory here"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "please add `var _ impltypes.ChaosImpl = (*Delegate)(nil)`"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use the `cleanExpiredFiles` method.",
      "reference": "nit: is this added deliberately?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the client_applications(:oauth_web_app).key?",
      "reference": "Given the number of tests which need this (I think I counted seven) should we maybe just install this one globally? Is there even a place to do that? Something in `test_helper` maybe?"
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function, but it's not a function.",
      "reference": "we don't use this anymore, so we can delete it."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `telemetryConfig.Enable` flag.",
      "reference": "nit: change to \"Telemetry configuration loaded from '%s'\""
    },
    {
      "prediction": "I think this should be the same as `bwb.WriteTo(&b)` but it's not the same as `bwb.WriteTo(&b)` but it's the same as `bwb.WriteTo(&b)` but it's the same as `bwb.WriteTo(&b)` but it's the same as `bwb.WriteTo(&b)` but it's the same as `bwb.WriteTo(&b",
      "reference": "Why did this value change?"
    },
    {
      "prediction": "I don't think this is a bug in knative-gcp.",
      "reference": "maybe `duckpubsubv1alpha1` ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The id is not mandatory for web extensions. Could you update this to support a web extension without an id?"
    },
    {
      "prediction": "I don't think this should be used in tests.",
      "reference": "I actually prefer them to be defined here. Client who calls `lib` should define the args, not `lib` itself."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I think this should've been done with the `defer`-named-return trick. I'll submit a PR for it."
    },
    {
      "prediction": "I don't think this is a good thing to do here.",
      "reference": "The bind address should be configurable."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Maybe the empty `delete()` should be implemented as default in the interface."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `input_file_name_(CMAKE_SOURCE_DIR/test/test_data/sample_data.h5`)",
      "reference": "How to ensure CMAKE_SOURCE_DIR is set correctly?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "safer to make a copy of incoming *big.Int"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "how did we choose this value? does this hold good for Windows too?"
    },
    {
      "prediction": "I don't think this is a bug in libcontainer.",
      "reference": "To follow the other build tags, maybe we can call it `criu`?"
    },
    {
      "prediction": "I don't think this is the default value for the `connect_timeout` parameter.",
      "reference": "Should we load this from the config file too?"
    },
    {
      "prediction": "I think this should be a problem?",
      "reference": "Can you file an issue for this?"
    },
    {
      "prediction": "I don't think this is the case for the `isClose` flag.",
      "reference": "@nbbeeken what were the cases where `!!this[kIsMaster]` was yielding an incorrect value? we should try to cover them in the tests"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `bolt_inventory`?",
      "reference": "This whole function feels messy. I don't have a better idea at the moment though."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `typeMap` property.",
      "reference": "should use Number instead of Long"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Can you rename this and the file `InfluxDBProvider` and `influxdb_provider.go` respectively?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is the real culprit, as now vlen will always be a Number (and known to the compiler as such). You could probably go one step further and avoid the ToBoolean on `vchildren` as well by writing something like `vlen = (vchildren !== undefined) ? vchildren.length : 0` if that matches the contract."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the customTabActivityHelper.",
      "reference": "missing space before `TextView`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "so this attribute is used as u8 in code, but saves as int32? Why?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "can RDSE be added to the list? It has its capnp files."
    },
    {
      "prediction": "I don't think this is the right thing to do with the type of injectable.",
      "reference": "These functions only ever read from the API and should always be reading from a cache, so I have made that explicit by expecting a Reader here and supplying a `cache.Cache` as the client."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "No, we can't skip any of the mangling after the suspend point: this should follow the other mangling and undo its push."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "this is generated code.. these changes will need to be made in the code generator to have them stick."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the shadow support.",
      "reference": "Should we abstract this into a reusable utility so it doesn't have to get repeated in every test file needing Shadow DOM support?"
    },
    {
      "prediction": "I think this should be a function, but it's not a function.",
      "reference": "Maybe we rename this to `command_monitoring.test.js` to match the directory name change? Or would you rather do that as part of the greater test cleanup? I'm fine either way."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why is this change necessary? `handleSingle()` will cast it to a string, no?"
    },
    {
      "prediction": "I'm not sure why this is the default name.",
      "reference": "This newly added method should be well defined, should it return `TableIdentifier` or just `String`?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "have a relation with a product"
    },
    {
      "prediction": "It is not possible to delete a local pod, but it is not possible to delete a local pod.",
      "reference": "I guess that there is still a window here, because the GC could happen between the `PodExist` and `Delete` calls. Would it be better instead to check `err` and allow it if it says \"pod has already been deleted\"?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "SQLAlchemy's session management does magic to make sure that if the rollback fails you still get the original exception that caused the rollback. Also it looks nicer."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This switch statement can be removed. Just return q.items[act.Nonce] != nil"
    },
    {
      "prediction": "I don't think this is the first child of a ForStatement, but it's the second child of a ForStatement?",
      "reference": "I think `==` for nodes is more readable than equals. An equals calls looks like it could be recursing, because intuitively two nodes are equal if their subtree are the equal. But everywhere you replaced, we don't want to test whether the subtrees are structurally equal, we want to know whether they're the same. Only `==` captures this intent, using equals obscures this. Not to mention that equals may NPE and is in that sense less ergonomic. I think we should enhance the rule with a list of types for which `==` is correct. Edit: in the meantime i think we could suppress those new violations..."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `--filter` option.",
      "reference": "What's the scenario for passing multiple filters?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "move to after check log.empty()"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This line needs to be removed"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Can we delete such const like `CloudBuildSourceEvent` and `CloudBuildSourceBuildId` since all those are contained under schemas/v1?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is unused."
    },
    {
      "prediction": "I think this is the default value for the context propagation.",
      "reference": "Any reason not to put `using System.Collections.Generic` (guess there shouldn't be naming conflicts)?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the response.headers.delete(\"X-Frame-Options\") and response.headers.delete(\"X-Frame-Options\") and response.headers.delete(\"X-Frame-Options\") and response.headers.delete(\"X-Frame-Options\") and response.headers.delete(\"X-Frame-Options\") and response.headers.delete(\"X-Frame-Options\") and response.headers.delete(\"X",
      "reference": "Could the name of this controller just be shortened to `TwitterCardsController`? Is the `Player` there adding information?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Backends with hostnames that depend on the request are always up?"
    },
    {
      "prediction": "I think this is a bug in pyramid.",
      "reference": "I'd rather catch those to `utils.py` and raise a simple ValueError from them. From the resource point of view, these are details of implementation"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "make this 1.0 ? I don't think all that many people do `language: julia` without any `julia:` specifiers, but may as well keep that possible?"
    },
    {
      "prediction": "I'm not sure if this is the case for the `azurekeyvault` command line.",
      "reference": "nit: `AZURE_KEYVAULT_AUTH_VIA_CLI` is defined by us, so it might be helpful to differentiate it from azure's env names. Maybe starts with `GOCDK`."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Depend on interfaces not on structures"
    },
    {
      "prediction": "This is a hack.",
      "reference": "This fix looks good. My concern, don't forget to fix metad too!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just noticed this nil context. Perhaps plumb through ctx too, or change to `Debug`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does it send requests with urlencoded bodies anywhere? I thought it sends only json. Maybe content-type should be `application/json` by default?"
    },
    {
      "prediction": "I don't think this is the default one.",
      "reference": "Again use of `constexpr` is recomended."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Minor point but I would call this ``redim_graph`` instead."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `cluster-api-provider-aws/pkg/apis/cluster/v1alpha2` package.",
      "reference": "As I was trying to figure out how the error messages are written out, since they are returned from `getOrCreate` and `reconcile`, it looks like we are using plain `klog` to write them out instead of using the logger from the scope above"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Now it's double logging, is not it? Because `service.ipForward.Enable()` logs extra `warning`"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Whatever the decision is about the request type to use, this should only match what is needed and not the other one."
    },
    {
      "prediction": "This is a hack.",
      "reference": "...and in turn, this should probably be var updatePreviews = true; if (!(localConnection && localConnection.type == Blockly.OUTPUT_VALUE) && (Blockly.localConnection_ && Blockly.highlightedConnection_)) { since the first clause is a no-op. If you want to leave it this way for clarity, that's fine too."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please remove this TODO, since they will not apply anymore after you are done. :) Can you please remove this everywhere else in this PR?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This seems like an incomplete schema definition. will that have any effect on the tests?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The testing cases are failing because `SetHeader` does not only handle cases where input are from files. It also reads categorical feature indices from the config parameters (see the part outside the `if (filename != nullptr) { ... }`). Skipping `SetHeader` directly here will cause errors when we load data from numpy or pandas arrays (where `filename == nullptr`) and use categorical features. So I think we should move the the check `filename != nullptr && CheckCanLoadFromBin(filename) == \"\"` into `SetHeader`. That is, we change `if (filename != nullptr) { ... }` into `if (filename != nullptr && CheckCanLoadFromBin(filename) == \"\") { ... }`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we should change the variable name of `err` in `if err, ok := err.(*exec.ExitError); ok `, this re-assignment of `err` still affects the next `else` branch"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`Status` has identical semantics with `StatusOr<bool>`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "why is this named in a different style from other paths?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Swapped these to ensure that we aren't passing a nil cluster in to util.IsPaused"
    },
    {
      "prediction": "I don't think this is a bug in the code, but it's a bug in the code.",
      "reference": "I don't see pkgManager used anywhere, is there a reason we need this?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "A bit late, but I don't think this is necessary, as all callers will send absolute paths. And if you ever get a relative path, resolving it with `toAbsolutePath()` leads to it being relative to whatever CWD the app is started with, while the typical resolving of relative `instanceDir` is to resolve it relative to CoreContainer#coreRootDirectory."
    },
    {
      "prediction": "This is a hack.",
      "reference": "There's an awful lot of test failures here because `localFieldPathType.schema` may not contain a `getters` array."
    },
    {
      "prediction": "I don't think this is the right thing to do with `concat_ws(' ', firstname, surname, email)`.",
      "reference": "Mysql allows for `||` concatenation (e.g. `firstname||' '||surname`) if you enable it: `set sql_mode=PIPES_AS_CONCAT;`. I think this check is safer though"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "NOTE: this is the default ENS registry address. If the ENS suite is deployed from the current builds to any chain, it will always be found at this address."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I'm curious why you are using `draw` in this route file?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Those variables are only been used once, I think we don't need to create them at all, just pass values to the `GetRawDiff` directly."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I like the idea of replacing all the `#if NET461` with `#if NETFRAMEWORK`... is that worth doing now? Means fewer changes if we go to 4.7.2 at some point  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "to fix the docs build failure, make this const var named without the suffix `Name`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This bugfix also included, in case a subjectAlternativeName was present in the cert, then URIs (e.g SVID SPIFFE auth) would not have been attempted."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Same here. Feels like the wrong location."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the command dispatcher.",
      "reference": "Please make `_path_suggestion` public (i.e. remove the `_`) in `downloads.py`."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "Woah, these flag names gotta get shorter. (Edit: I'll try to suggest some if needed, will think on it.)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `app.secrets.secret_key_base` or `app.config.secret_key_base`?",
      "reference": "Is this the code that's supposed to use the Rails app's only when in Rails4? What's the point of the first `if app.respond_to?(:secrets)`, both the `if` and the `elsif` have the same body, is only the second one needed? If `app.config` has a `secret_key_base`, then use it, the end. Is there a need for first checking if `app.respond_to?(:secrets)`?"
    },
    {
      "prediction": "I don't think this is the case for objc enums.",
      "reference": "Does this not apply to C enums on Linux?"
    },
    {
      "prediction": "I think this is a bug in the server, but it's a bug in the server.",
      "reference": "Should this check if the error is `RetryableWriteError` before adding the label?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Oh wow, that's one complicated require :)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "do you mean how to \"use\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We can't really test this anymore since ref and props.ref are at the backing node level now"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "Did you intend to set this in the constructor?"
    },
    {
      "prediction": "I don't think this is the default one.",
      "reference": "This looks fine as a first approach, and can we put a TODO here about ubuntu 18.04 being hardcoded?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This isn't strictly needed since lmdb / leveldb data that is unencoded does not require OpenCV IO. I think `DataLayer` should only require lmdb / leveldb. If one tries to use encoded data without OpenCV the `DataTransformer` guards will report the dependency failure."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Should we take out this change? This was only in there to try to brute force the start of the apiserver yesterday."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `has_many :approvers, through: :approvers, source: :approvers, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy, dependent: :destroy,",
      "reference": "I worry that this association name is a bit confusing. Yoz was asking me about the concept of completion yesterday, which is why I think of it. It wasn't clear to him exactly what it was. what about calling this a `step_completer` ? we know that a proposal has many steps, so I think that might be clearer. in the future, we also might want the rename the `approver` relation because a step is not always an approval these days."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Just add a to-do saying we need to add api-version in the check some time in the future when we enable the single-swagger spec mode for validation."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@lunika Please see this. It allows us to do `Propel::getConnection()` easily, as we have only one database."
    },
    {
      "prediction": "I don't think this is the right thing to do with `scope.Span.Tags` and `scope.Span.Tags` as `scope.Span.Tags`",
      "reference": "Not related to this particular cast but I wonder if we shouldn't have a cast helper that would log if null to gain visibility."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "why do we need to explicitly declare these fields?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Note that there are multiple OAI servers -- that's why `$serverClass` is a variable here. You'll want to fetch `$serverClass` from the service manager rather than a hard-coded value, and also set up a module.config.php for the authority record version, `VuFind\\OAI\\Server\\Auth`. Should be easy enough since it can share the same factory."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is no longer needed and should be removed."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "could use named return params here to avoid declaring the opts, and using naked returns instead."
    },
    {
      "prediction": "I don't think this is the case, but I think it's the case, but I think it's the case, but it's not the case.",
      "reference": "this is an unrelated fix. I noticed when an instagram carousel post is mixed with images and videos, the videos don't come with thumbnails, so I am adding a fallback thumbnail for this case."
    },
    {
      "prediction": "I don't think this is a problem with the `runStateTransition` method.",
      "reference": "\"... after protocol version 1\"?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Is there a unit test that covers this regexp? I am afraid that changing it might break things =/"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change is okay IMO because an `@` variable in Ruby is not a reference -- `@` variables are instance variables. Also, it's never used by the Ruby transformers."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why this change was needed? Because in `po` files it's with curly braces?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Wait -- where did this change come from? This seems unrelated to trace building and seems like it could affect basic execution, unlike the rest of this PR which is all under the off-by-default trace option. Please separate this into its own PR and probably ask @AssadHashmi to review."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "seems to be redundant (mention `docusaurus`   )"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we combine this with the Rollback API? We could still support the `rollback` method here, but combine `Rollback` and `CherryPick` into something like `ManageSnapshots`. Then we could reuse logic for enforcing checks of the current snapshot. What do you think?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Maybe just `env_prefix`, I don't think this is referring to the WQ manager."
    },
    {
      "prediction": "I don't think this should be imported in the future.",
      "reference": "Unrelated line change :)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I raised an eyebrow at making `net` depend on `k8s.io`, but it seems we're already doing that."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think ticket meant, not applying replacement in this method, but rather applying encodeSomeHtml to each and every localization string"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "ticket for the 4.0 epic?"
    },
    {
      "prediction": "I don't think this is the case, but it would be better to do this.",
      "reference": "`cfg.model.get('neck')` will return None if neck does not exist, thus we can omit the default value."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Trailing whitespace detected."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I don't see why a `cxxflags` key is necessary? C flags are important in the target file because they define things like the float ABI. But these flags are also used for C++. I can't think of a reason why you would want to configure C++ flags in a target file."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Update year range in Copyright notice, and elsewhere too."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Can we update this PR to not be a breaking change? i.e. if a user specifies `accessKeyID`, it is still used. But if a user specifies `accessKeyIDSecretRef`, it takes precedence?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `read_tou` parameter.",
      "reference": "You don't actually need both tests here as \"truthiness\" means that `\"0\"` is false and hence the first test will be true..."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Everything else in here is using `I18n`. Should we do that here to be consistent?"
    },
    {
      "prediction": "I don't think it's a good idea to use `config:\"port-list;udp:53,udp:67,0.0.0.0/0:tcp:2379,0.0.0.0/0:tcp:2379,0.0.0.0/0:tcp:2380,0.0.0.0/0:tcp:2379,0.0.0.0/0:tcp:23",
      "reference": "What do you think about changing the ordering to be `<protocol>:<cidr>:<port>`? I think it matches the most with what we previously had so that it doesn't change too much for our users."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I'm fairly sure this precondition is always true due to the mod (%)"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I love seeing diffs like this one, adding a `String` message to an otherwise cryptic `assert`! It makes me realize you must have had a hellacious debugging session!"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "1. No logger exists to produce a message 2. Can't assume the latest version because missed version means 0."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "I saw a wrong reuse of the cache between a partial analysis of a single file and a full run where errors due to lack of context on the first partial run was reported on the full run. Shouldn't we use a hash that is composer.lock + psalm.xml + command line to be safe?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Could you also update it in `at_time`?"
    },
    {
      "prediction": "I don't think this is the default value for the locality option?",
      "reference": "Because schema is non-final we can't just switch this to a lambda"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "proposal: **always** add the exception to the end of the message. So no need to to pass exception twice (implicit and explicit). Need a lot of changes."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "why? event.getInvocationType is not you want?"
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's a string, but it's not a string, but it's a string.",
      "reference": "nit: how about `GitSHA`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "If you move the other functions, this should also be moved to `makeflow_gc.h`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This whole block bugs me. Expire_time to me suggest that an absolute time of when something happens and duration is an interval of time. While the code looks correct, it feels awkward to read."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `_dom` property.",
      "reference": "Can we add `_dom` as an argument to createVNode here? I think it might be shorter (could totally be wrong!)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "I think that the iret handling is not yet good."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Huh, that's kinda weird. I get it, but it's unexpected to me..."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "why is this removed? it is important when you upload from stream of unknown size"
    },
    {
      "prediction": "I'm not sure why this is the right thing.",
      "reference": "Out of curiosity, why is this needed? Does it enforce what class can be assigned?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "non-blocking: Now that we have a handful of statements which deal with creating a listener, it may make sense to introduce a `createListener` method or something similar"
    },
    {
      "prediction": "I don't think this is the default implementation of this class, but I don't think it's the default implementation of this class, but I don't think it's the default implementation of this class, but I don't think it's the default implementation of this class, but I don't think it's the default implementation of this class.",
      "reference": "factory should be stateless if possible, looks like much complexity added"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Could you please add short description for the default value as well?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Leave a TODO message to say we will fix the log level in the future, once committing the block and the state become a transaction"
    },
    {
      "prediction": "I don't think this is the default value, but it's the default value.",
      "reference": "this can be integer"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nitpick: Please remove the blank line here"
    },
    {
      "prediction": "I don't think this is a problem with the `changeset_id` field.",
      "reference": "What is this for? The only methods I can see by that name in the rails doc are generating a foreign key name from a model class name but you seem to be giving a key name as argument?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Is this second check necessary? we know that just after the plugin was created its metricRegistry is null, it's set only after `initializeMetrics` has been called."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "shouldn't this be `return TALKACTION_BREAK;` as the player does not meet the required group access?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "does this still work if minerNode1 has already proposed a block before 2 & 3 are stopped?"
    },
    {
      "prediction": "I don't think this is the case for the TestCloudLogging E2E tests, but it's not the case for the TestCloudLogging E2E tests.",
      "reference": "I am wondering if we can either make this a feature or have a way to turn it off in production. My concern is that we might be adding more of these kind of code in the future."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "We can just use `.stack()` here? Then I guess we can reuse when supporting multi-index columns."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What are the possibilities here? Since we plan on supporting .net standard 2.0 from day 1, we might as well tackle that now."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should the parameters be called reference or context?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need to also change `length` here (and below) to `bytesize`? Perhaps we ought to make a copy of `in_buffer` encoded as binary and then the existing algorithm should work."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This should be `toDisplayString()` to not contain e.g. passwords."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "Can we just say that having a non-nil `autocomplete_path` implies that autocomplete is enabled?"
    },
    {
      "prediction": "I don't think this is a bug in the Caddy server.",
      "reference": "Note that the package github.com/golang/protobuf/proto is deprecated. We're instructed to use the \"google.golang.org/protobuf/proto\" package instead. I didn't want to change it now to avoid intrusive changes whose consequences are, currently, unknown."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `as: :terms, id: 'terms'",
      "reference": "Are these gone routes? Do we need to 301 them?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "move them to internal group of imports"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "can we rewrite this as: `ignored event '%s' for cstor pool '%s'`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "not all client data types have an approving official (eg: 18F does not). do we still want to include the relation here?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This change should also probably go into the corresponding method of the abstract By class?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why this remove?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "As the test failures indicate, making this change is going to mean changing everything which currently implements this interface."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Do we want to redirect this to the forum or something in case people have it linked/bookmarked?"
    },
    {
      "prediction": "I'm not sure if this is a `member.name` or `member.email` or `member.email`?",
      "reference": "@peterzimon came up with this 'NM' piece as a placeholder for New Member initials, without this the screen looks broken. It changes to normal initials calculation once email or name is entered. Lmk if you'd like to put something different here ;)"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "@kevinansfield Would be cool if you can take a   if this is the best way to add `subscriptions` info on member model. This uses the transform + separate model definition way which seemed to be the right way from other references in Admin  "
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "This is the common way of dealing with optional dependencies"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: we can replace all `kr` in this file with like `src`."
    },
    {
      "prediction": "I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string.",
      "reference": "same concern here as above"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `criteria.options.fetch(:read)`.",
      "reference": "Thank you for this, I gather this repairs failures that I've seen in another PR."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This place probably makes sense to me. We can consider exposing an argument to make the dedup step optional (I am not sure it is a good idea but I want to think this through together). The dedup step we are adding is going to trigger a shuffle. Technically, we are fine in the existing expire snapshots action as it does the dedup in `except`. The question is what kind of performance impact deduplicating here will have. We only have duplicates if multiple manifests reference the same files. In `rewrite_manifests` procedure, we rewrite all manifests, meaning we produce a snapshot with new manifests where entries are old data files. Also, there are updates and deletes that may rewrite manifests. I think deduplicating here makes sense to me in all cases. Thoughts, @rdblue @flyrain @RussellSpitzer @karuppayya?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can we move the code before deleteNodeFromDB ? this way even if the node crashes after remove config we can still re-run decommission again ?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "Seems the default value of `melt`'s `var_name` at namespace.py should be changed as well."
    },
    {
      "prediction": "I don't think this is a problem with the botocore_parser_integration_test.",
      "reference": "I think botocore's serializer should already create the correct headers. However, they are currently not used in `_botocore_parser_integration_test`(line #217). Maybe we could remove the headers here and just use a fallback in the `_botocore_parser_integration_test` (i.e. use the given headers if they are set, otherwise use the headers generated by botocore's serializer)?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `confirmAction` and `confirmAction` and `confirmAction` are the right thing to do with the `confirmAction` and `confirmAction` parameters.",
      "reference": "This code is passing a non localized string when it should be passing in a localized string or it should use the name of the item being deleted."
    },
    {
      "prediction": "I don't think this should be a string, but it's not a string, but it's a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's a string, but it's not a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "in case you want to rename one of the plugins when instantiating, from options?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This default variable should be moved into a config variable, created by `package_context`, and read from `config\\package_layout.json`."
    },
    {
      "prediction": "I think this should be a function, not a function, but it's not a function.",
      "reference": "Can I ask you to add a new line after `const` assignment? I believe that this increases the code readability by encapsulating assignment and logic (expecting) blocks."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So the intention is you configure with `-CMAKE_CXX_FLAGS=\"-D KOKKOS_IMPL_TURN_OFF_CUDA_HOST_INIT_CHECK\"`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was a bug."
    },
    {
      "prediction": "I'm not sure if this is the right place to use lazy loading?",
      "reference": "Is OK that we don't have some placeholder?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Sectorbuilder behaves differently depending on whether it's given 1 or more threads. It won't seal if only given 1."
    },
    {
      "prediction": "I'm not sure how to import this, but I'm not sure how to import it?",
      "reference": "Sort of believe We should put MetricManager in constructor parameter given this case."
    },
    {
      "prediction": "I'm not sure why this is a class, but I'm not sure why this is a class, but I'm not sure why this is a class, but I'm not sure why this is a class, but I'm not sure why this is a class, but I'm not going to be a class.",
      "reference": "Do we need to check `fieldId` is larger than 1000?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this should be called after the if below (the one for disable positive acks)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd like to avoid changing this method since it is public and using a URI will probably change behavior for users passing strings (String -> URI -> Path instead of String -> Path)."
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "Should these restore the stashed env after the test runs?"
    },
    {
      "prediction": "I don't think this is the default argument?",
      "reference": "We're calculating the full list of kwargs here (even if the first element of the list would return True) so we could improve performance by using a generator line 408 in ``for default_node in all_defaults:``."
    },
    {
      "prediction": "This is a hack to make sure that the ndeltas are correct.",
      "reference": "Can ndelta differ depending on when the deltas are compacted? That is, when intermediate updates are dropped?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Our checkstyle config likes it better when the `<p>` is before the first word of the next paragraph, and not on a blank line"
    },
    {
      "prediction": "I think this is a bug in CRIU.",
      "reference": "This looks to be the only place where we return early before the close below, so if the \"double close\" is bothering people, closing manually here (and removing the `defer`) could be an option"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `qunit` task.",
      "reference": "This task can probably be deleted since we don't need gulp to run Jest."
    },
    {
      "prediction": "I don't think this is a problem with the `SocketPoller` module.",
      "reference": "Doesn't this need to include `Errno::ECONNRESET` to fix the issue?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "never heard of a qirector... what's their role again? (also should be 'for a movie')"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Implement the \"collect all props for one vertex\" logic inside QueryVertexPropsProcessor"
    },
    {
      "prediction": "I think this is a bug in Rai::uint256_union::decode_dec?",
      "reference": "This is to prevent parsing things like \"1.1\" as \"1\" until we implement it properly."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Can we change `_getCheckpointParentDir` to be a public function explicitly? It seems like something that clients of experiment runner may wish to use."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Why is a restart necessary?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should setting the task runtime also go under the above if condition?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "SPIRE uses the leadingLowerCase convention for unexported constants"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The newest JSchema code generator orders `System` usings first."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I understand that we want to have a possibility to configure the IcebergInputFormat to be case sensitive or case insensitive since it can be used by other MR jobs as well. Do we want to allow the users of Hive to shot themselves on the foot and enable case sensitivity? My first guess would be that we should not use the configuration here, just go with `false`, but if you have some specific use-case in your mind I can be easily convinced  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Will the above call to cStorPoolAddEventHandler() get executed in the same thread as this line?"
    },
    {
      "prediction": "I think this is a problem?",
      "reference": "I don't think alloca instructions are always at the start of the entry block. I think it would be safer to check the entire entry block for alloca instructions, just in case some are not the first instruction. (Technically they can be anywhere in the function but we check in other places that this isn't possible)."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why isn't this 4789 (which I think is the Felix default)?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Can this be `Import operations failure`? In addition, is this the right time to change the variable names? e.g. `ReasonImportOperationsFailure`, `ReasonImportFailure`, `ReasonImportSuccessful`, `ReasonCreateResourceFailure`, `ReasonImportResourceSuccessful` Naming convention that i have assumed here is as follows: `Reason<Action><Entity/Adjective of the Entity><Sucess/Failure>`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I suspect this isn't needed because I think `rb_intern` gets marked already."
    },
    {
      "prediction": "I'm not sure if we're using a WebDriver-backed Selenium, but I'm not sure if we're using a WebDriver-backed Selenium, but I'm not sure if we're using a WebDriver-backed Selenium, but I'm not sure if we're using a WebDriver-backed Selenium.",
      "reference": "This change is incorrect: the current log level is correct."
    },
    {
      "prediction": "I don't think this is the right thing to do with the current version, but it's not the right thing to do with the current version.",
      "reference": "Can you add a space before the equal sign? There are a couple other places where spaces are missing in this PR."
    },
    {
      "prediction": "Should we remove this?",
      "reference": "Please follow the todo naming convention."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "These are no longer used and changes should instead be made directly to the files in `deploy/chart/crds`   /assign @JoshVanL /unassign"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this really necessary to work around this way? The old version works fine with me when converting to ONNX."
    },
    {
      "prediction": "I think this is a bug in s3Blob.",
      "reference": "Same as above: don't start error strings with a capital letter, and don't fix unneeded things in an unrelated commit ;)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this a testing debug statement?"
    },
    {
      "prediction": "I don't think this is a problem with the `parse` function.",
      "reference": "you'll need to wrap the _whole thing_ within this async call (or refactor it so everything below is in a new temporary function). The code below this section depends on a value for `object` after the parsing occurs, but what you're doing here is kicking off a race condition where `object` is null, but _might_ parse quickly enough to assign it the parsed parts. Instead, you need to do everything that depends on the parsed object in the callback of `parse`."
    },
    {
      "prediction": "I'm not sure if this is a thread. I'm not sure if this is a thread. I'm not sure if this is a thread. I'm not sure if this is a thread. I'm not sure if this is a thread. I'm not sure if this is a thread. I'm not sure if this is a thread. I'm not sure if this is a thread. I'm not sure if this is a thread. I'm not sure if this is a thread.",
      "reference": "This is now going to be protecting `stopped` when it doesn't need to. If you are going to do this then can you make `stopped` non-atomic and protect it in `stop`. It's cheap to make a `unique_lock` fyi, it's just a pointer to a mutex and a `bool`. The `lk.lock ()` in the loop is superfluous so probably shouldn't have been there to begin with."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `github.com/mysteriumnetwork/node/config/remote`",
      "reference": "Lets not give packages names if we dont have to. If a package requires a rename, we should change the actual name while/if we can."
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack.",
      "reference": "Not sure I see where this is coming from. This is a bug fix? Should be mentioned in the commit message? Same below."
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function.",
      "reference": "I reverted this change in the last commit, I think we should revert it here. I know this leads to confusing test output for skipped tests, but I would prefer to tackle that in a separate PR specifically focused on that problem. In fact, I think the issue might really be with the leak checker, and not how this test runner is defined. Please make a ticket for this (if it doesn't already exist) and revert this change"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Can this part be done in `dataset.get_ann_info`? Just like CocoDataset converts xywh to xyxy in `_parse_ann_info`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we change the name of this test struct to be `testTracerProvider` as well?"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core.",
      "reference": "\"google.golang.org/grpc\" should be together with \"go.uber.org/zap\" all \"\"github.com/iotexproject/iotex-core/*\" stay together"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "No need for a separate variable here - just call `utils.read_file` directly below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Thanks for the fixing, small question, Here the message just be written to the channel, will it be blocked?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "maybe we will have something like `Bodies []byte(\"bodies\")` instead of them being a number? with numbers we are making it harder to insert stages mid-process."
    },
    {
      "prediction": "I'm not sure if this is a group member.",
      "reference": "out of curiosity, why making this change? If no real reason, could you restore to avoid unnecessary changes of several generated files?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Could we public events if `manager.serStatus()`?"
    },
    {
      "prediction": "I think this is a bug in Uppy.",
      "reference": "could be misread as `<body>`, maybe something redundant but very clear like \"before the closing `</body>` tag\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This test is specifically checking behavior on sync I/O (note there are tests with Write in the name, and other tests with WriteAsync). Enable sync I/O here."
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `email_body_text` and `email_cta_label` and `email_cta_label`.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I don't think this is a problem with the `CStorVolumeClaimSpec` type, but it's not a `CStorVolumeClaimSpec` type.",
      "reference": "nit: Should we have something like `volumeName@snapShotname` and this will be filled only if it is a clone creation"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This seems like an improved pattern :)"
    },
    {
      "prediction": "I don't think we need to import the snakebite module.",
      "reference": "I think it would be better to have a separate configuration option for specifying which HDFS interaction layer to use instead of using the existing hadoop version option. I think there are still cases where things might have to rely on Hadoop version for other things, and overwriting that information with \"snakebite\" would make that difficult. The existing hadoop version option could still be used to distinguish the different HDFS CLI flavours."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why are we filtering content twice? It seems like just filtering it in PAL should work."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "These should probably move to `constants.js`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Again, you don't want to depend on glassfish."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `Faker::Space.launch_vehicule`?",
      "reference": "it should be `Faker::Space.launch_vehicle`, otherwise it will crash"
    },
    {
      "prediction": "I think this should be the first time the archive is created.",
      "reference": "Isn't it quite expensive to check whether the file exists on every write?"
    },
    {
      "prediction": "I don't think this is the case where we want to use `webdriver.http.CorsClient.isAvailable()`?",
      "reference": "Please hide this behind a flag and add a setter function to the builder."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "old api should be deprecated if we don't intend on using it anymore. Again this should happen through swagger api and then removed from next release. We should also release not this as a breaking change. (same with all the other cloudsnap api renames."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "so strange...... canTcpListen is to detect, if this transport can init when customers deployed vertx and servlet rest transport, we must detect which one will be used only both of them refused to init is a problem. we have already print that......"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Did you mean for this to be `FORM`, instead of `FROM`?"
    },
    {
      "prediction": "I don't think the user data is gzip-compressed.",
      "reference": "What are your thoughts on the long term solution for the naming of this variable? Do you think we should revert the logic when we are ready to make the next set of breaking API changes?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There's a syntax error on this line."
    },
    {
      "prediction": "I think this is a hack, but I don't think it's a good idea.",
      "reference": "You lose the value of `result` when you `goto out`"
    },
    {
      "prediction": "I think this is the same as the `set` method, but it's not the same as the `set` method.",
      "reference": "Just a style thing, why not `this.ratio_ || 0`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think the stdlib's `net.IP` has a `Mask()` method, does that do what we need?"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think this is a good idea.",
      "reference": "Why does substitute need to be public? Are we allowing/encouraging variable usage when using Daisy as a library?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should probably use ctrl-enter if `tab` is given, just like in `follow_selected`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This file looks like anti pattern `ServiceLocator` and lucky it's not used anywhere. Can I remove it? (in separate PR)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "we can just have this method call the next, passing in the file metadatas (deduplication of logic)"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "What happens here if you send the `wheelEvent` directly to the `tabbed_browser` and let it take care of propagating it to its children (i.e. the focused tab)? If that works, I guess that'd be cleaner."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "it seems python 2 don't support `end=''`. @StrikerRUS @henry0312 any better solution? or we drop the support of python 2?"
    },
    {
      "prediction": "I think this is a bug in VkImageViewCreateInfo.",
      "reference": "This test already exists in the object_tracker layer."
    },
    {
      "prediction": "I don't think this is the best way to do this?",
      "reference": "Same here, can we presume if `privacyParameters` is set we need goQuorum handling? Or is there a goQuorum sub option in `privacyParametes`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The addition of delete files in `newManifests` far above the addition of data files threw me a bit. Is it intentional to ensure the delete files are at the front of the list?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Interesting. The call to `Array(groups)` below this would seem to indicate this doesn't _have_ to be an array. I think the problem is actually that passing a hash to `Array()` actually converts the hash to an array of key/value pairs rather than wrapping it in an array. So maybe `Array(groups)` should be `groups = [groups] unless groups.is_a?(Array)`."
    },
    {
      "prediction": "I think this is the default value for this property, but it's not the default value for this property.",
      "reference": "This is not a particularly good default but we need it to keep the old behavior."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We have other tests to assert all properties of a condition are valid. It's enough to assert the condition is not nil here."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `openflow` package.",
      "reference": "shouldn't the import be renamed `crdv1alpha1` by convention? It seems that you took care of renaming everywhere else..."
    },
    {
      "prediction": "I don't think this is the default value for the `PauseContainerTag` and `PauseContainerImageName`",
      "reference": "nit: Can Linux-specific paths be moved to a conditionally-compiled file for Linux?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is not the right approach. The `Distributor` maintains a model of the current state of the Grid. That model already contains the information about every active session. We don't need to modify `SessionMap` to expose it further."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Git doc seems to suggest `for-push` is a optimization. Do we have a plan/ticket for treating them differently?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This not necessary since you moved the layers to `contrib/`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I think this also needs to be removed from `resources/bolt_bash_completion.sh`, `rakelib/pwsh.rake`, `lib/bolt_spec/plans.rb`, and `lib/bolt/config/options.rb`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "I fixed this today with a direct push to master. My build was failing otherwise."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "not sure why this is in a \"rule\" child package from the interface..."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `fieldToLabel` method.",
      "reference": "Not needed, please remove."
    },
    {
      "prediction": "I think this is a bug in h2o_url_compare_hosts.",
      "reference": "Shouldn't the logic be: * the result is a mismatch if either is a unix path but the other is not * if both are unix paths, then perform case-sensitive comparison * if both are not unix paths, then perform case-insensitive comparison"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `google.golang.org/protobuf/cmd/protoc-gen-go-grpc` package.",
      "reference": "This is just rearranging it alphabetically"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think this disables it for the rest of the file - you should be able to use it inside of the function instead."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "this could receive the MediaInterface directly or an identifier, it is correct to type it with int|string? or just use mixed?"
    },
    {
      "prediction": "I don't think this is the case for a multi-leaf field comparator.",
      "reference": "Why not return `Object[]`?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Looks like we are trying to match the new ordering of fields in `ManifestFile`. Earlier, we co-located `...FilesCount` with `...RowsCount` to match the ordering of methods in `ManifestFile` and args in constructors. Is this change intentional?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "You're already setting drop loot to false just above."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`once` is very generic and doesn't specify it's purpose - `closeOnce`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why did this need to change from `private`? Oh for the test below. And this is only a test class too.  "
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Should test the `has?` method here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think you want to be asserting/clicking $saveLink, not $link."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't have `target_name` on `@sensor` - why introduce it for `@asset_sensor`? If we do want to introduce it everywhere, can we just call it `job_name` to avoid introducing a new term?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Missing copyright header (+other new files)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we do the flag check here as well to check whether or not we have enabled the \"Handle without timezone\" flag here as well? We may be using this not on the read path (like in the migrate/snapshot code) and it would be good to catch it here as well and make sure users know what is happening."
    },
    {
      "prediction": "I don't think this is a problem with the `pipeline_definition_definition_sensor` module.",
      "reference": "why is the file named `pipeline_definition_definition_sensor`?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "None not needed, can just be `return`. not important for this release"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think it's missing closing `</p>` tags in line 108 and 109 unless they don't matter..."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `autoStoreScriptVariables` and `enableScriptEngineCaching` and `enableFetchScriptEngineFromProcessApplication`.",
      "reference": "So it seems that loading a script file from the classpath needs to be enabled explicitly now since this is `false` by default. Is it possible to enable this via the YAML config file in a Camunda Platform Run distribution?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "can we delete any code in the provider implementation? i imagine the entire thing is unused now?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I suggest we remove all these unused functions. I don't expect any external projects to be importing packages from `cert-manager/test/...`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like the template argument doesn't resolve by default so you need `std::lock_guard<std::mutex> lck`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Are we removing this public method? Could it be useful to someone? Maybe we could implement it once in Node using the metamodel"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I think this method is unused now?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I know we discussed this before and decided to reuse the AntreaPolicy gate. But do you think realization status will introduce much overhead or not?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `edge_core` and `edge_site.log` and `edgesite.log` and `edgesite.log`",
      "reference": "please add a blank line at the end of this file. Applicable to similar cases below"
    },
    {
      "prediction": "I don't think it's a valid host, but I'm not sure if it's a valid host.",
      "reference": "This is not really needed, the line added in `GridNodeConfiguration.java` is what really fixes the `remoteHost` regression."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "filterCache can be null"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If strstr returns NULL, the check on 378 won't fire, because param_name will be at least SET_PARAM_CMD_LEN."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this change affect the performance of other algorithms, except KMeans?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What do these changes have to do with the request ID?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I'm kind of surprised this doesn't require `typename`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `go-algorand/logging.json`?",
      "reference": "nit: move this one down."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "maybe 'standard Tukey boxplot definition' if it is standard? Otherwise sounds like it is just *a* definition for boxplots..."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `git-tree-state` option.",
      "reference": "I feel we should not fix this."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think these are not necessary"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please update the user guide too."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "If you use `compact('name', 'code')` here, you'll get an associative array, which might make the rest of the code more readable (instead of using hard-coded 0/1 indexes)."
    },
    {
      "prediction": "I'm not sure why this is the right thing to use.",
      "reference": "Should it be 2011-14 instead ;-)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I want to write some type of test for this but there are not Getter methods to assert this value. I tried to extract the value via the stats that are exposed without luck."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `gsuite_id` argument.",
      "reference": "This needs to take the group id, not the gsuite id."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "These should use the constants defined in JsonTests.cs"
    },
    {
      "prediction": "I don't think this is the case for the `search-console` plugin.",
      "reference": "Kind of unrelated to this PR, but let's update this to `getDataErrorComponent( 'search-console', error.message, false, false, false, error )` so that everything is passed as expected."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": ":obj:\\`dataset\\` cannot be correctly rendered"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `existing_bookmark_for` method.",
      "reference": "I think `email` is something we get from devise, and I think the goal of putting it in the generator was not to tie others to that particular implementation?"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "If the span producers pushing to the queue do so faster than the this can drain, it will cause this to hang. I'm guessing we can update the `enqueue` method to check if the `stopCh` is closed and not send any more spans while this flushes what has already been pushed."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Not sure about that, an array is iterable right? But if I pass array, that clear method wont work"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "make sure the config changes stuck. are there any invalid config values? maybe write tests around empty `trust_domain`, negative/missing `ttl`, invalid `key_size`, etc..."
    },
    {
      "prediction": "I'm not sure if `window.__mochaResult__` is set to `window.__mochaResult__`.",
      "reference": "Why are you changing this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@phirefly Can we look at a list of RWAs, or ask someone to double-check that this format is correct? Otherwise :shipit:"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `option(SparkWriteOptions.TARGET_FILE_SIZE_BYTES, writeMaxFileSize())`?",
      "reference": "Still request a local sort for bin-packing based on the defined table sort order."
    },
    {
      "prediction": "This is a hack.",
      "reference": "As with the other PR, user name is better."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "a peer's accounting lock is held during `Pay`. we should avoid adding additional blockchain calls here if possible."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `Sync` property.",
      "reference": "Maybe wording could be improved. Is this \"not enabled\" or it is \"not available\". Not sure about that."
    },
    {
      "prediction": "I think this is not a good idea to do with the `conditionalBranchesEvaluated` function.",
      "reference": "I looked at the new `conditionalBranchesEvaluated` function and it looks like the part added is a duplicate of the line above?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "can you put this flag in `blockRefInfo` instead? It would be a shame to add one more file per block, especially since we've run into inode limits. I guess `blockRefInfo` should maybe then be renamed to `blockInfo` or something. But we're stuck with the filename."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't we keep other parameters if only IP is empty? Or maybe return an error if it's a mandatory argument?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Was this just wrong before? The names indicated types but type wasn't specified. I guess the tests passed as comparison worked with ``type=None``?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "icebergCol.name() is the unqualified column name"
    },
    {
      "prediction": "I think this should be an array of arrays.",
      "reference": "It's generally a bad idea to use mutable types like lists as default values for parameters. Lots of strange, difficult to debug side effects can occur. I see that there was already one example of this prior to this commit which probably explains why it seemed innocuous to add more but I'm going to rework this before committing to master."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `prettier` module.",
      "reference": "We run prettier as an eslint plugin, so this harmful"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Check if the TypeDescriptor and MemberDescriptor includes are necessary"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `k8s.io/apimachinery/pkg/apis/meta/v1` or `k8s.io/apimachinery/pkg/apis/meta/v1` or `k8s.io/apimachinery/pkg/apis/meta/v1` or `k8s.io/apimachinery/pkg/types`",
      "reference": "delete the empty line here."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Line is too long. [89/80]"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "You don't need to expose this method to do what you want. There are already public addNewGetMapping, addNewPostMapping, and addNewDeleteMapping methods."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "This test passes in `dev`. Why wouldn't this work?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "ARN -> Amazon Resource Number (ARN)"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure how to do this?",
      "reference": "Why not use the overload that takes an instance?"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core.",
      "reference": "`Blockchian` is a misspelling of `Blockchain` (from `misspell`)"
    },
    {
      "prediction": "I think this is a bug in NvidiaGPUManager.",
      "reference": "`agent/gpu/nvidia_gpu_manager_unix.go:47: struct field lock has json tag but is not exported`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: better rename to `TEST_QUEUE_ARN` or `TEST_EVENT_SOURCE_ARN`"
    },
    {
      "prediction": "I don't think the user wants to manage configuration themselves.",
      "reference": "Would this mean that podMonitorSelectors suffer from the same issue if they are the only configuration set?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`ctx` is unused in GetEnvironment"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "We usually use OkDialog()"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `--privacy-unrestricted-enabled` option.",
      "reference": "could we please change that to something that indicates that this feature is not \"production\" ready!"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "swim -> swin. Other configs and file names also should be modified."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: arg description for \"key\"?"
    },
    {
      "prediction": "I don't think this is the case for the `fs.NodeFsyncer` interface, but it's not the case for the `fs.NodeFsyncer` interface, but it's not the case for the `fs.NodeFsyncer` interface, but it's not the case for the `fs.NodeFsyncer` interface for the `fs.NodeFsyncer` interface for the `fs.NodeFsyncer` interface.",
      "reference": "If we don't have a `dir` yet, we wouldn't need to do a sync right? If so, perhaps we can just `getStoredDir()` like `Attr()`?"
    },
    {
      "prediction": "I think this is a bug in libdynamorio, but I think it's a bug in libdynamorio, but I think it's a bug in libdynamorio, but I think it's a bug in libdynamorio.",
      "reference": "I still don't seem to fully understand this. Why are we testing the host if DR_HOST_NOT_TARGET is not set?"
    },
    {
      "prediction": "I don't think this is a test.",
      "reference": "in the current implementation, both schemes are supported (you can call either `/bzz` or `/v1/bzz`). i would suggest to keep it this way"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "hmm, I think we can just do `new Error(assembly.error)` and that should set `error.message` correctly too. I don't know why it was done this way with a separate `.message` assignment before :sweat_smile: Should we do `error.assembly = assembly` so the template editor can access it that way, rather than parsing `error.details`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should never be empty. The access field always needs a value of at least `c:0` or `r:0`"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "Another question is, do we want to call `os.Getenv()` every time we parse a file? That seems a lot."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "minor: please rename all occurrences of `A` to `T`. please also rename `v` to `value`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Do we want it to be so dynamic? My first idea was to base it on SyncConfig.BeamSync ."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can you change this instead to just `type.toString()` and then you wouldn't have to expose the getBitMask in the enum. (Alternatively you could have used `type.hashCode()` but that doesn't feel as nice)"
    },
    {
      "prediction": "I think this should be a problem?",
      "reference": "I'm confused by these tests. Shouldn't the template string `@importance_type@` have been replaced with the actual value of `importance_type`?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Let's keep using NewKeeper so that it got covered by tests."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I only see new imports. Is there any functional change in this file?"
    },
    {
      "prediction": "I don't think this is the case where we don't want to do this.",
      "reference": "ineffectual assignment to `err` (from `ineffassign`)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Would you mind removing the default parameter above? (I doubt I'll ever use defaults again since you still have to protect against callers explicitly passing `null` or `undefined`)"
    },
    {
      "prediction": "I don't think this is a good idea to use the rdkit.rdBase.LogToPythonStderr() function.",
      "reference": "Make sure the old logging functions still work, but add deprecation warnings (unfortunately Python suppresses deprecation warnings by default, so I'm not sure if anyone'll notice)."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Not directly related to the topic of this ticket: I think this API design is a bit confusing. To disable delemetry, I would write `managementService.enableTelemetry(false)` which is not intuitive to read. Maybe `toggleTelemetry` instead of `enableTelemetry` is more clear."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Again I suggest returning `AnnotatedCodeLocation[][]`."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "We should probably require an increased verbosity to output for anything below the cluster itself to avoid spamming the logs. It would also be good to give additional context as to what we are attempting to reconcile since the controller has multiple workers."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not needed anymore"
    },
    {
      "prediction": "I think this is a bug in Datadog.Trace.ClrProfiler.",
      "reference": "Am I right in thinking this completely avoids the situation where `enable_calltarget_state_by_ref` is `true`, but the managed integrations don't expect a by ref argument? For example, if there's an exception here, that seems like a fatal problem, as we would have a mismatch for jit rewriting? We should disable instrumentation entirely in that case shouldn't we? i.e. if this (or the existing `EnableByRefInstrumentation`) calls fail, should we bail out of this method entirely as we can't safely instrument?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "nit: spaces seem off"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "shouldn't the em parameter be called ec?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please change this to use o.DidSign(o) as implements this logic without performing any of these checks that duplicate something that JWT can do correctly. If the JWT deserialized properly, and DidSign returns true, the JWT was signed by one of the listed operator keys."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Talking about style, IMO extracting either `getComponent()` or `getPubDate()` to variables would make this line easier to read."
    },
    {
      "prediction": "The \"License\" file is distributed under the \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, which is not included in the \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND.",
      "reference": "package header missing"
    },
    {
      "prediction": "I'm not sure if this is a Suspense, but I'm not sure if this is a Suspense, but I'm not sure if this is a Suspense, but I'm not sure if this is a Suspense.",
      "reference": "Just a thought (doesn't change the output or anything) - do you think we'll ever want to access the other properties of `oldVNode` from within `_childDidSuspend`? If so we could pass `oldVNode` here and then check these properties in the _childDidSuspend implementation. I don't have strong feelings either way, just occurred to me."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `parent` parameter.",
      "reference": "We should be configuring the base paths somewhere.."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "May also need to test the normal functionality with min/max_sizes"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "We can remove this one. It's just a random one I got for free for testing."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `data-acquirer-id` attribute?",
      "reference": "(maybe this should be MyDevice or just removed entirely?)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Can you do a nil check here, as the task isn't always nil here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here. I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "`lodash` shouldn't be grouped under WordPress dependencies"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Does order matter? Should we sort by enode key to make duplication checking easier?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you explain this too? This seems to go beyond linting."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I just moved this into the render.js UT file since this test doesn't actually use an components"
    },
    {
      "prediction": "I think this is a bug in ddevapp.",
      "reference": "We do have to capture and check the err here right? I don't think we need to capture the location of the file though for this context."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "an unused import"
    },
    {
      "prediction": "I'm not sure if this is the last one to be parsed, but it's not the last one to be parsed, but it's the last one to be parsed.",
      "reference": "If this value doesn't exist (do an `, ok := ...` check), we should initialize and store it"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Would use parenthesis to explicitly state the associations of operands ```js const MAX_SAFE_INTEGER = Number.MAX_SAFE_INTEGER || (-(2 ** 53) - 1)"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `onReceive` method.",
      "reference": "This handle is now private to pyserial, but if there is no public function to retrieve it I guess this is the best we can do."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This function is what **the compositor** calls when it wants to fullscreen a client, not what the client calls."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "s/not existed Pod/non-existing Pod"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Why did we not leave this as just `svcDescriber`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "nit: I think we've been (in)consistent in leaving a blank line here."
    },
    {
      "prediction": "I think this should be a column, not a column.",
      "reference": "Maybe we can change it to a more generic name like source_id."
    },
    {
      "prediction": "This is a hack.",
      "reference": "What's the theory on why this could fix the hang? It seems like the call to `GetRootNodeForTest` will always need to call into the crypto object before returning an error, and so it should block on that `c` receive, after which the test immediately drains `errCh`. So I don't quite see how buffering would help..."
    },
    {
      "prediction": "I don't think it's a bit in the vex.vvvv, but it's a bit in the vex.vvvv, but it's a bit in the vex.vvvv, but it's a bit in the vex.vvvv.",
      "reference": "Maybe add an assert in arch_init or somewhere?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I wonder what does this `// nolint` ignore? And what are the standards that you choose which error to fix and which to ignore?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "what about the line below, forceUpdateCollection?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `cmd_line_array` and `cmd_line_array.compact.reject( &:empty?)`.",
      "reference": "Doesn't this go in the opposite direction of #1051 / #1062 by putting platform-specific logic back into this module?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think this is the only line in JS legacy code that should be updated based on the renaming. `global.googlesitekit.setup.isAuthenticated = response.authenticated;` would be sufficient to keep the old name for the legacy JS data (which will be phased out in the long term) while supporting the new name in the API route. All updates to the JS components above wouldn't be necessary."
    },
    {
      "prediction": "I think this is a hack. I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Technically, this would allow `pingWaitTime` to be `false`. I don't know if it matters here."
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "I only want the proxy request for this to run for kinesalite. So this just returns true if the KINESIS_PROVIDER is kinesis-mock"
    },
    {
      "prediction": "I think this is a bug in this file.",
      "reference": "Please add your name to the list of copyright holders."
    },
    {
      "prediction": "I don't think this is the default value for maxRetryTimes.",
      "reference": "Maybe maxRetryTimes should be bigger than 2. Return Max(maxRestryTime, 2)?"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Call `userName` is good enough, `signedUserName` is narrowing the actual usage of this method."
    },
    {
      "prediction": "I don't think this is the case where we want to add/remove the correlation identifiers to the scope manager.",
      "reference": "How would you feel about a static method to express intent?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Do we know for sure that no other code changed its value? (Maybe some weird testing use case or something) Why not just use the actual value instead of risk lying?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `go:generate dbgen -i root.sql -p account -n part -o partInstall.go`",
      "reference": "the partInstall.go isn't an auto-generated file, and the part.sql doesn't exists either."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "`k` is unused in PutHash"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Use IOUtils instead"
    },
    {
      "prediction": "I think this should be a mocked one?",
      "reference": "It's not related to the line of code, but I don't know how to write it in a more proper place. Looks like `e2e/myst-provider/db/myst.db` should be in `.gitignore` file and should not be commited."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nice touch since Google likes to change things every now and then."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Make `CircuitBreakerManager` implement `PluginInfoInitialized`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is extra awkward, QVariant.convert() takes a QMetaType which takes the value of a QMetaType.Type."
    },
    {
      "prediction": "I don't think this is the right thing to do with a context.Context.",
      "reference": "Nit: finished -> finish, \"done passing it\" -> \"passed it\"."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe mention that it will be saved to the filesystem otherwise?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Probably cleaner and more general to do this: string,Format(\"Column {0}\", i+1) That way if the local language has a convention like \"3 column, this is\" it still works."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This can be uniformed too"
    },
    {
      "prediction": "I think this should be a function that returns an error, but it's not a function that returns a function that returns a function that returns a function that returns a function that returns an error.",
      "reference": "It looks to me that this does not have to be exported."
    },
    {
      "prediction": "I don't think this should be used in tests.",
      "reference": "It looks like this is only used in order to extract the snippet file names from GapicProviderFactory. I wonder if it would be better expose the snippet file names directly, without exposing a test-only function in non-test code."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Another question: this is being removed, but I don't see a corresponding removal if it being called? Was it never used (or am I just missing it)? (is it related to what was in the onclick that got removed, i.e. was that supposed to call this and not something in the backing bean?)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Suggestion: `.. does not have an Approved condition set to true`"
    },
    {
      "prediction": "I don't think this is the case for the test_id, but it's not the case for the test_id, but it's not the case for the test_id, but it's not the case for the test_id.",
      "reference": "I would say that client class should have default of False and Cloud prov should enable deleting."
    },
    {
      "prediction": "This file is part of the .NET Foundation project.",
      "reference": "Did this remove the BOM or something?"
    },
    {
      "prediction": "I'm not sure if this is a rule, but it's not a rule. I'm not sure if this is a rule. I'm not sure if this is a rule. I'm not sure if this is a rule. I'm not sure if this is a rule. I'm not sure if this is a rule. I'm not sure if this is a rule. I'm not sure if this is a rule. I'm not sure if this is a rule.",
      "reference": "This makes the BlockHeaderValidator mutable, and IMHO should not be done. Note we have a builder that has the exact same method, so instead of mutating a produced BlockHeaderValidator we should hook into wherever the builder is being created."
    },
    {
      "prediction": "I don't know how to do this with `async=True` or `async=True`?",
      "reference": "May be add information about parameters to the doc string while at it?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Naming of this sounds a bit awkward. Perhaps priv_legacy_getTransactionCount or priv_legacyGetTransactionCount?"
    },
    {
      "prediction": "I think this is a bug in VkDeviceMemory, but it's a bug in VkDeviceMemory, but it's a bug in VkDeviceMemory, but it's a bug in VkDeviceMemory.",
      "reference": "This one should probably be added to the list in #24 . It's possibly indicative of an issue, but there isn't a VUID for it."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `project` and `network` parameters.",
      "reference": "Why this indentation change? Seems the original indentation would be fine, and leaves more room."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Would be nice to know what the `update` argument does in the docstring."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think we can just use `io.BytesIO` here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This ensures that the User-Agent header matches during replay."
    },
    {
      "prediction": "I don't think this is the best way to do this.",
      "reference": "What units are used for this default?"
    },
    {
      "prediction": "I don't think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "I am wondering if it makes sense to make this a flag to `flatc` rather than a preprocessor flag, since this is generated code, it would make more sense to simply omit this code completely if the flag is not specified"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Doesn't this change the behavior (edit: oh, I see, never mind)."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I think you need a `do` at the end of this line."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Not passing in a `:params` key here."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Feels like this should be an option and not the default. Leaving them running would give you immediate response to claims, which might be what some people would want. Hibernation is AWS only right now and probably other clouds will just disregard the setting but arguably validation should be rejecting attempts to create / update powerstate on gcp/azure/etc. I'd pitch we put this onto the pool spec and make you opt in."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think I saw somewhere that it has been fixed and that you can use #NETCOREAPP3_0_OR_GREATER but I may be wrong."
    },
    {
      "prediction": "I think this is a hack, but I think it is not possible to change the current state to the initial state.",
      "reference": "what's the second part for?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It's not clear to me what the \"super\" test above is for. As far as I can see, the test runs a spellcheck for \"super\" but then uses \"fob\" as the index into suggestions, which will never find an entry."
    },
    {
      "prediction": "I'm not sure why this is a bug in iotex-core/ioctl/util.",
      "reference": "revert this file change"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "I think this is the most elegant way to allow us to still fail on `I`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Wouldn't it be better to use a sql `IN ( :exact_value )` ?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `timeout` option.",
      "reference": "So far this is not working as expected... working to further investigate WinRM protocol and the gems behavior."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "So now there're two ways to get requests: `ScenarioExecutor.get_requests()` and `Scenario.get_requests()`. To avoid confusion we should probably make `Scenario.get_requests()` method private, or hide it in some other way."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "This existed already, but seeing as you are changing the variable to have an explicit type it could be made a const reference to remove a copy."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I don't think this code is being tested; this method can be removed without the test failing"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `doInBackground` method.",
      "reference": "@codepoet2017390 You have already initialized this ArrayList in the onPreExecute method then why do it here too?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `Gsa18f::Procurement.new` instead of `Gsa18f::Procurement.new` instead of `Gsa18f::Procurement.new` instead of `Gsa18f::Procurement.new` instead of `Gsa18f::Procurement.new` instead of `Gsa18f::Procurement.new",
      "reference": "This covers the `RESTRICT_ACCESS=true` x non-gsa pair, but we probably want to test the three other permutations: (`RA=true`, gsa), (`RA=false`, non-gsa), (`RA=false`, gsa)"
    },
    {
      "prediction": "I'm not sure if this.focusTimeout is set.",
      "reference": "Please don't do this - if you want to disable code permanently delete the code, if you need to disable it to test don't commit. Such sections are very poorly highlighted during review and can cause unspotted issues slipping through the process..."
    },
    {
      "prediction": "I think this is a bug in OVS.",
      "reference": "I'm starting too feel we have too much abstraction and too many interfaces here. But this method is definitely the most confusing IMO. For one, it's called \"Get*\" but it does not return anything... I don't have a good understanding of what's going on anymore, so it's hard for me to suggest an alternative, but it's pretty clear to me that this interface needs to be rethought. An interface where all the parameters are themselves arbitrary objects (`interface{}`), whose actual type depends on the specific interface implementation, is not a helpful abstraction"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It fills me with endless sadness that we can't use Selenium's own `SessionId` here."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Interesting. So you've found that it's faster to request only the \"Stat\" without the data so long as this is the typical path?"
    },
    {
      "prediction": "I don't think this is a problem, but it's not a problem.",
      "reference": "Is this a future fix? I thought the local identifier scope and the package issue were the same one."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the root of the treeInterceptor.",
      "reference": "Not super important, but this line could be split up."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Maybe we should better call the dispose function without checking the value of `item.data` (since the dispose function is setup before `data` is set up)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why set to GPU, is it CPU?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `Ember.computed` or `Ember.computed('i18n', () => `Ember.computed('i18n', () => `Ember.computed('i18n', () => `Ember.computed('i18n', () => `Ember.computed('i18n', () => `Ember.computed('i18n', () => `Ember.computed('i18n`)`)`)`)`",
      "reference": "This should be `computed('i18n.locale'....`"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "can we not expose the channel directly? or at least expose it as a read only channel?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Can we add a `--with-bashcompdir` here to override this? I'd like to be able to do unprivileged builds."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "We will be removing this maya/volume package completely. Do not use this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why you think that `model_ptr` will be `nullptr` when memory allocation is failed? I think `new daal_knn::Model(column_count)` would throw `std::bad_alloc` if `operator new` is not overloaded. Is it overloaded by DAAL in the way it simply returns `nullptr` in case of bad allocation?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the miner.",
      "reference": "Where does this 0.001 come from? Is this from the network collateral cost function, which happens to be hardcoded right now? I think it's going to rot very quickly: it depends on sector size and (probably) block height."
    },
    {
      "prediction": "I think this file is a bug in Illinois Open Source: https://github.com/IllinoisOpenSource/IllinoisOpenSource, Illinois Open Source: https://github.com/IllinoisOpenSource, Illinois Open Source: https://github.com/IllinoisOpenSource, Illinois Open Source: https://github.com/IllinoisOpenSource, Illino",
      "reference": "Please update the license header in each source file. For more information see: #2697"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `onOk` and `onError` arguments.",
      "reference": "!numbers -> numbers"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "so we don't have universal rules afterwards? In that case I'd remove this entirely (and maybe some places where it's used get cleaner) since we shouldn't ever add a universal rule. Not only because it's way simpler in TS, I'm also just super skeptical about \"universal\". In case of this rule, even control characters may have their place in Swaggers, e.g. in `examples` sections where you can have raw response bodies where control characters are perfectly valid."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the child process.spawn?",
      "reference": "You're welcome to surface this option through the API, but I'm not going to make this the default behavior."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just a thought that any further extensions of `buildBinaryFor` signature could be done as `buildBinaryFor(..., opts... BuildOptions)` for better readability."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'll fix the InMemoryExporter right after this PR lands"
    },
    {
      "prediction": "I think this is a bug in VUID.",
      "reference": "Good call, none of these are technically invalid"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "this one should be updated too"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "maybe need to add microserviceId too."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "I'm curious, do you create this commit at the very end by rebasing and taking the value you had after moving everything ?"
    },
    {
      "prediction": "I think this should be removed when the trimRows plugin is used, but it should be removed when the trimRows plugin is used.",
      "reference": "It's no longer possible to use `modifyRow` to trim rows and that's ok to use TrimRows instead. But I think we should move this test to TrimRows plugin tests as `trimRows` setting is not a part of the `core`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "The function seems to either return \"default\" or return the extension stripping the preceding dot. Does the fact mean that we can no longer register `.default` as an extension?"
    },
    {
      "prediction": "I think this is a bug in the docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker-docker.go.",
      "reference": "this may require a statefile version update"
    },
    {
      "prediction": "I think this should be removed in 2.0.",
      "reference": "I like when `@deprecated` contains how to resolve it - eg. \"use `SplFileObject::fgetcsv()` instead\". The information in upgrade notes is usefull only during upgrade."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Nice to see that your local environment is up-to-date now for these changes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Instead of setting it to null, i think lets set it to {}"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We should bump this before releasing and remove all legacy fields that are safe to do so. Since we cannot have multiple versions anyway there's little value in walking around with the \"alpha\" stamp."
    },
    {
      "prediction": "I don't think this is the right thing to do with `x$san_enabled` and `x$san_enabled` and `x$san_enabled` and `x$san_enabled`",
      "reference": "I might suggest a different name for the `DEEPBIND` config.h macro. Perhaps `FLUX_DEEPBIND` to give a hint in the code that we're using a locally provided define."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Code generated by protoc-gen-go. **DO NOT EDIT.**. The correct way to fix `deprecated` in this file may be updating the protoc / protobuf / grpc and regenerate this file."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "We should make sure that we cover the testcases in a new unit test class."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Is this only used in test code? Is there future utility in it for production code? If not, it would be nice if this could be moved into a test package. I'm not sure how hard that would be. CC @laser"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Super curious how you noticed this, as SPIRE itself currently only configures once...?"
    },
    {
      "prediction": "I'm not sure if this is a Datafile error, but it's not a Datafile error.",
      "reference": "This `startsWith` seems a bit brittle because in the code base we'll occasionally spell it \"DataFile\"."
    },
    {
      "prediction": "I don't think it's a big int, but I don't think it's a big int.",
      "reference": "if it keeps reconnecting for too long, how should we get alerted?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "it's better to use single name style in one name."
    },
    {
      "prediction": "I think this is a hack, but I don't think it's a hack.",
      "reference": "As defaultSendPort is being removed, and I don't like TODOs on examples, please remove the whole line"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Should we return `nil` when `err == errChangeSetEmpty` instead of calling l.103 `WaitUntilStackUpdateCompleteWithContext`?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Hmmm I thought spotless would wrap this line, but it doesn't seem to complain about it"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "I think this will require updating the api version. we are planning to do this anyways, so perhaps we can lump this in so we don't have to update too many times?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "revert this for parity"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "INCR_BATCH and DECR_BATCH could be exposed as tuneable command line options but that might be too low level to expose. I think keeping private for now where \"in the know\" folks could use to try and tune makes sense. These values were choosen mostly \"at random\" and have worked out for us thus far."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Currently this isn't very clean because we have to re-use some of the predefined parser types - the demo uses WRITER_U_CTAGS but there should be some support for custom writer type."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `response.body`?",
      "reference": "I think this was left it accidentally :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you finish re-ordering this list to match the one that was deleted?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Do we need to check if `exp.Target.StressChaos` is `nil`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `cstor-volume-create-listclonecstorvolumereplicacr` or `cstor-volume-create-listcstorpoolcr`",
      "reference": "not calling this is going to impact current functionality which depends on PVC.. let us still call this and set the values to default as 'none' (or empty) by handling the error from 'get' operation"
    },
    {
      "prediction": "I don't know how to write to the eventfd?",
      "reference": "`!=` is no the same as `<`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "No need to create a dir for transformer. Simply move transformer.py into mmdet/models/utils/"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "Can't you just add `SelectSubscriptionActivity` directly to the manifest instead of opening `MainActivity` that then starts it?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `app.Flag(\"run-check\", \"Run the check during package build\").Bool()`.",
      "reference": "Maybe say \"the spec's %check section\" so it's clearer what we mean."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is sorted.",
      "reference": "I think after change this check `rowInMapper === null` is always false, so it's useless."
    },
    {
      "prediction": "I don't know how to do this with LPI2C_CLK_PODF (DIV1) and LPI2C_CLK_PODF (DIV1) and LPI2C_CLK_PODF (DIV1)",
      "reference": "ClockIpLpi2c4.Enable() is required. The same change is required for enablePeripheralClocks()."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "nit: this should be `SHA` since it is an acronym for `Secure Hash Algorithm`, no?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Not sure if Intl can be defined but not `Intl.DateTimeFormat`. Both seem to have the same percentage on CanIUse."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "PTAL, looks like the order of PVC & PV is reversed for different storage-engine types, for Jiva/CStor the args sent to sendEventOrIgnore are `PV, PVCName`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Remove the trailing white space"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "No need to modify this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "would be nice at some point to clean this signature up... not relevant for this PR"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, so it's not a string, so it's a string, so it's not a string, so it's a string, so it's not a string, so it's a string, so it's not a string, so it's a string, so it's not a string, so it's a string, so it's a string, so it's a string.",
      "reference": "Here, is it `null` because it is `null` in `$fieldConfiguration`, or because it has been set to `null` above in the `array_replace` ? If it doesn't exists at all in `$fieldConfiguration`, I think you should add `type => 'text'` above in the `array_replace`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I was thinking about this for #2928 too, which also uses `endsWith`... Presumably `SomeOtherObject` would match `endsWith(\"Object\")`, meaning that something more sophisticated like splitting it then iterating right to left would be needed in order to do this robustly?"
    },
    {
      "prediction": "I don't think this is the default value for the BatchExportProcessor.",
      "reference": "I think this name is a bit confusing because if you asked someone what type of exporter they were using they would probably say Zipkin or Jaeger, etc. How about `ProcessorType` with `Simple` and `Batch` definitions?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`req` is unused in RecreatePipedKey"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The \"Adsense\" term needs to be capitalized - I just noticed this was wrong through ACs and IB, so not a problem of the PR itself really. I'll quickly fix it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "do which methods need to be registered? is it basically just the ones that are directly referenced in ParDo calls? (The Beam GoDoc doesn't say anything about it. :/ )"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "@bmckinney does this mean that the bibtex citation will be available via API?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We should probably tag the cliquet-fxa version as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "IIRC we need to use memset, because an empty brace is not C99 comformant, and because we cannot use `{0}` because how the struct is organized is not defined in POSIX (the initializer cannot be `{0}` if the first property of the struct is a struct)."
    },
    {
      "prediction": "I don't think this is the default value for the `serviceAccounts` field.",
      "reference": "Will we be adding this to `AppliedTo` as well? If not, any reason why not?"
    },
    {
      "prediction": "I think this should be accepted.",
      "reference": "Just a note that this feels weird being on the base NVDAObject rather than IAccessible, but right now, I understand that's how it has to be because we fire MSAA caret events on the focus object regardless of whether it's IAccessible. I think we should consider restricting these caret events to focus objects that are IAccessible subclasses in future, but that change is probably too risky for this PR. CC @MichaelDCurran for his thoughts."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This change and other similar ones should not be part of this commit. This commit is about adding a ImageUploadType not fixing controllers and stuff."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I am a bit confused about PING here. Ping is implied and it overlaps with \"$SYS.REQ.ACCOUNT.%s.%s\" where the last token is what is requested (CONNZ) and the one before is the requested account id."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit: use the OptSubFolder constants. Also in the client you are using \"maxdepth\" but in the server the constant for \"depth\" is being used."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I also moved this to `/verdaccio/storage` since it's written in runtime, and the approach here is to make the configuration by default read-only."
    },
    {
      "prediction": "I don't think this is a good idea to use `gax.EventEmitter` or `gax.Promise` instead of `gax.Promise` instead of `gax.Promise` instead of `gax.Promise` instead of `gax.Promise`",
      "reference": "nit: s/has cancel method/has a cancel method"
    },
    {
      "prediction": "I'm not sure why this is a problem with `with_questions`?",
      "reference": "Useless assignment to variable - `second_quiz`. Use `_` or `_second_quiz` as a variable name to indicate that it won't be used."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is this still needed since there's the `GzipPrecompressed` type?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this is spelled wrong and also not used so remove it"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It might be right here that's the issue ^"
    },
    {
      "prediction": "This is a hack.",
      "reference": "@danieldietrich let's leave existing extension. Here we just mark `keyComparator()` with `@Deprecated` annotation"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the SOFTWARE.",
      "reference": "This breaks CI. I am not sure why you need to include io.h in this file especially on linux."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this seems equivalent"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "change size to 50MB criticial, 10MB warn... change count to 50k critical, 5k warn..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This has nothing to do with master/slave replication. Is this something we want to change too? If so, I guess this is an aggregation?"
    },
    {
      "prediction": "I don't think this is a bug in RSpec.",
      "reference": "Maybe it makes sense to mention that those zombies are not forever, but only up to the moment when the parent process exits? Is that correct according to your observations, @benoittgt ? Please disregard this note if zombies remain after."
    },
    {
      "prediction": "I don't think this is the right thing to do with the mocking.",
      "reference": "moto mock setup needs to happen before boto usage."
    },
    {
      "prediction": "I don't think `first_metric_only` is not available at the same time.",
      "reference": "`hasattr(cb, 'first_metric_only') and cb.first_metric_only` -> `getattr(cb, 'first_metric_only', False)`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "no newline for function"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "This makes me feel icky. We could also go the route of making `wlr_output.scale` a double instead of a float, but that would be a more widely reaching change."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Again, would be awesome if you could remove the tabs in these 3-4 lines as well."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the way name?",
      "reference": "You're moving multiple times from `step.name`; you're not allowed to do that. Instead you have to copy the `step.name` string and (if you want to) move once at the very last."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I",
      "reference": "What about `may not end`? @jancborchardt"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "If you think about it, the status should be PermissionDenied?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Calculation looks good but don't know what format etc grafana expects this to be in."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: We could use the `to_str(..)` util here. (let's not bother changing for this PR..   )"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.tasklist.",
      "reference": "Can you rename alias to `executiongenpb`. The rule is package+\"pb\" for `temporal-proto` and package+\"genpb\" for server protos."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Any noticeable performance hit? Any other way to avoid the allocation and copy even of the array?"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think this is a good idea.",
      "reference": "What if you remove this line entirely from here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`on_lateral` can also be implemented"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Please add a space between `if` and `(`."
    },
    {
      "prediction": "I don't think this is a problem with the `zpool` operator.",
      "reference": "This statuses might have been better off with some custom status type. However, good for now."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Thanks for catching the bug. Here your change lets `v4IPNet` and `v6IPNet` take the first IPv4/IPv6 address in `addrList`. Maybe choose the last one also works and makes code simpler? What's your idea? @tnqn"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "nitpick: you can name this variable just `details`"
    },
    {
      "prediction": "I don't think this should be used.",
      "reference": "The character class in the regex should probably be \"[a-zA-Z0-9_]\"."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please also increment `Settings.VERSION` and update `AccountSettings`."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think this should just say \"build <date>\". And when builddate wasn't set, e.g. somebody built weave with 'go build' or some other way, this should return \"unknown\"."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we move this into a separate var and call it `desc` like below?"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "why RpcSchema need this annotations?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Not sure it makes sense to send the reply if we did not delete from the map, but I guess it does not hurt.."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Most of these variables can be moved after `return` or to the body of `if` statement."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit: Is this actually just a http \"unauthorised\" response? Or is that too vague? If this is the right way to go ... is \"token\" the right word\" Or do we want to say something else?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with config.boltdir.path?",
      "reference": "We check for `$future` in PuppetDB::Config, so this won't change behavior if you don't have `future` set."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think you should remove `if isinstance(by, str):`,. We also should fix the error message `raise ValueError('Not a valid index: TODO')` to match with pandas'"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Curious - do we want this to be `OTel.GrpcHandler.Request`? For example, if someone is debugging a crash dump, they would get some hint that it was added by OpenTelemetry."
    },
    {
      "prediction": "I don't think the commit state is unknown.",
      "reference": "nit: unnecessary `</p>`"
    },
    {
      "prediction": "I'm not sure if this is a HDF5Reader, but I'm not sure if this is a HDF5Reader, but I'm not sure if this is a HDF5Reader, but I'm not sure if this is a HDF5Reader, but I'm not sure if this is a HDF5Reader, but I'm not sure if it's a HDF5Reader, but I'm not sure if it's a HDF5Reader, but I",
      "reference": "Should just be `#ifdef ADIOS2_HAVE_HDF5`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "FYI: I deployed a stack with multiple lengths for the stack name and resource id to cloudformation, to see how it truncates the parts for the final FunctionName"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Did we not use this field @_@"
    },
    {
      "prediction": "I don't think we need to use `this.androidKeyAlias` or `this.androidKeyPassword`",
      "reference": "shouldn't this be `android_keystore_name`?"
    },
    {
      "prediction": "I think this is a bug in v1alpha2.",
      "reference": "Double check the issuers package too :)"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is out of date right? Now that `_is_first_level_self_reference` uses it as well? Perhaps we should make the docstring more general and not refer to method names that could change."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This test alone takes around 10-12 minutes to run. It has 20 subtests each of which takes around one minute. We should see if we there are redundant subtests that we can remove, or look for a way to optimize them."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Good call, we need to keep that check :+1:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should the interface have 2 `ParseHeaders` methods?"
    },
    {
      "prediction": "I think this is the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value for the default value.",
      "reference": "Nit: Does this make more sense as `iceberg.hive.metadata...`? The rest of the configs seem to start with `iceberg.hive`."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Is `baseURL` not required?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just delete it, `embedding_rpn_head` is not a `Detector` which should have `show_result`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Where do we _get_ tag values? edit: I mean, where are these `GetFoo()` methods called from? It just seems weird to me that we are getting tag values from spans. I thought we only ever _set_ tags on spans."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This seems like log spam. Maybe expose the encoding as a method and log at the point of interest?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I looked up that one, and it seems correct: Authentification is French, Authentication seems to be correct"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Can we print a more human-friendly warning here, saying that plotting won't work or something along those lines?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `http` and `http.Response` and `http.Message`?",
      "reference": "@mhils didn't we try to get rid of these (now empty) wrapper classes?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I would avoid importing `felix/ipsets` package because this package is the windows equivalent and should be at the same level of `felix/ipsets`. We could add linux specific dependencies into `felix/ipsets` later and it will break Windows build."
    },
    {
      "prediction": "I don't think this is a problem with the `registerTable` method.",
      "reference": "Maybe, `import` would be a better name."
    },
    {
      "prediction": "I don't think this is the default value for `max_results` and `page_size`.",
      "reference": "Wouldn't we want `PARAMETER_MAX_RESULTS` in here as well? (I might be miunderstanding how this is used)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We can re-use the config in our tests."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Wouldn't we have the same issue with the internal libevent? IIRC, the integration is pretty close to an exact duplicate. Or does the libevent m4 code already take that into account when setting this variable? PMIx _requires_ libevent, so it isn't like pmix_libevent_support can be anything other than 1. I'm okay with leaving this question for separate resolution - just wondering why we don't have the same issue here."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "The actual User-Agent string uses \"CriOS\" not \"CRiOS\""
    },
    {
      "prediction": "I don't think this should be used.",
      "reference": "Unused code deletion. Is that a desired thing? No implementation of this actually used this indexer, so removing it seemed reasonable (and was suggested by the compiler). Maybe this had an indexer so plugins could use it? This change is definitely pushing the limits of what is appropriate in a \"cleanup\" as it is changing public API surface area."
    },
    {
      "prediction": "I think this is a bug in the puppet.log file.",
      "reference": "We'd lose the data here from the original teardown_exception and only get the dump_exception - I fear that that could make the actual error difficult to track if it cascades."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "At this point in `diff()` we should know if we're dealing with a `component` or a native `html` element. We can reuse that information in this if-statement here :+1:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "somewhere in reward protocol, we need to do if epoch is Fairbank { a.foundationBonusP2StartEpoch = genesis.xxx a.foundationBonusP2EndEpoch = genesis.yyy p.state(sm, adminKey, &a) } that is to write the 2 new values at Fairbank height then this logic can follow"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Dropping and recreating would delete all t he previous records, are they any important?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "While it is technically OK to use `m.GetPaths()` here, and it's a mock code so it doesn't really matter, I'd still like to have `m.Path(\"devices\")` used here, because since commit 714c91e9f73a1512808476eb532b4aa36bbb7530 we're not supposed to use GetPaths() for anything other than state save/restore."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Let's be consistent everywhere: either \"Disable\"/\"Enable\" or \"Disabled\"/\"Enabled\". I'm voting for the latter.:)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this works and is the smallest possible change but we could definitely fail earlier"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Should not have snuck in here right? This is a golang 1.17 feature, wii definitely want to update these"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Could you explain the logic with prevFolderId?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with a clock.Clock.",
      "reference": "Please add license header"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It bothers me that the user calls `initialize` without also calling `finalize`. It seems to me that we're essentially making `lbann_comm` a singleton object. Going further down this path, we would put `initialize` inside `lbann_comm`'s constructor and `finalize` in the destructor. This has it's own weirdness - the user must make sure it's lifespan matches the beginning and end of the program. We may also run into the case where someone might want multiple instances of `lbann_comm`, but this is not too important."
    },
    {
      "prediction": "I think this should be a test, but it's not a test.",
      "reference": "We should probably make a unique_ptr<ROMol> typedef in ROMol.h and start using that liberally."
    },
    {
      "prediction": "I'm not sure if this is the default value for `fillHandle` or `autoInsertRow`?",
      "reference": "Can you add missing asterisk?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "late to the party, but I bet it meant to be `capitalizeLettersAfterNumbers` :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The Activity is recreated on configuration changes and the value of the field is lost. So, e.g. pressing 'send' once will display the error message. If you rotate the device and press 'send' again, the message will show another time. Use `onSaveInstanceState()` and `onRetainInstanceState()` to save and restore the value of the field."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like a \"find and replace\" unintended change here"
    },
    {
      "prediction": "I don't think the SP has learned anything yet.",
      "reference": "haven't we got rid off `randomSP` recently? (I think `not learn` implied that)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why we need use `in.GetStatus()` function here? Can we use `in.Status.xxxx` directly?"
    },
    {
      "prediction": "I think this is a problem with the renewal lock.",
      "reference": "@cretz Just a thought: what if another renewal process updates the certificate between the beginning of this for loop (above on line 67) and actually calling RenewCert? Even though we have a read lock on the certCache, something else could have renewed it by now, and finished, which would cause this certificate to be renewed twice. Could you double-check my thinking here and see if that's a plausible 'race' condition? I wonder if the lock needs to be put over this whole function. (It's still early here; I could be wrong...)"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is a PDEBUG_CLIENT.",
      "reference": "We don't need this for the PInvoke?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "nits, I think add a log (using s.logger) to show why does this return with no error is better."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Btw, It would be nice if we have some tests for those validation functions."
    },
    {
      "prediction": "I'm not sure if this is a static class.",
      "reference": "Should this be called something that indicates its function, rather than its content? validationMessagePrefix, or similar?"
    },
    {
      "prediction": "I think this is a bug in NVDA.",
      "reference": "Please remove this line"
    },
    {
      "prediction": "I think this is a bug in XCode 4.2.",
      "reference": "You could change the name of the command line switch too. Short options are typically one character after hyphen. wxWidgets' command line parser seems to handle `-nd` without confusing it with `-n` or `-d` but I'm not sure if that's by design or by accident. I'd remove the short option. `--no-daemon` is with hyphen but the rest of Manager and client uses underscore. Please change that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I think this is a bug in the TDNF spec.",
      "reference": "Why are we mentioning toybox in this message? AND it still says \"tdnf error\". What's the actual error? Should it be resolved instead of flagged?"
    },
    {
      "prediction": "I think this should be a better error message.",
      "reference": "You can remove these if they've been resolved in NODE-3405 and this isn't depending on it"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "don't need the class here if its empty"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `i18n` macro.",
      "reference": "This should be computed('i18n.locale'...."
    },
    {
      "prediction": "I don't think why this is a problem?",
      "reference": "Please add return and return type description to docstring of this method."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `id` parameter.",
      "reference": "What does 1 << 32 do? In irb typing this yields 4294967296. I didn't find the append operator in Numeric or Integer."
    },
    {
      "prediction": "I don't know why this is the case.",
      "reference": "We generally use metadata for this sort of thing, indeed there is a `metadata[:execution_result]`."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `stream_data` option.",
      "reference": "This was very confusing until I realized this might refer to the *bokeh* use of the word 'streaming'."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you rename this as `tasksToContainerStates` ? If you do that, you can rename the lock as well"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Fixing `lint` warnings that have existed for a while."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "An iterator **of {\\@code n} sequential elements,** where each element ~are~ **is the** given {\\@code element}."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "If all of the `SqlCommandIntegrationName` values are the same, can we just remove it from `IAdoNetClientData` entirely and put the constant there?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe regroup this import with the other cert-manager packages."
    },
    {
      "prediction": "I don't think this is the default behavior.",
      "reference": "There are spaces missing ;) Just have a look at the code style of the `if` statement above"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should pass the size limit as a parameter to Drain so that we don't take messages out of the pool and then drop them. It's ok to merge as is, I will file an issue."
    },
    {
      "prediction": "I don't think this is the case for a ARM/AArch64.",
      "reference": "Patch lists are used in many places so this is going to break other updates. This should just be a local change in emit_special_ibl_xfer() to pass the second-to-last instruction instead of the last instruction."
    },
    {
      "prediction": "I think this is a bug in the code, but it's a bug in the code, but it's a bug in the code, but it's a bug in the code, but it's a bug in the code.",
      "reference": "@argakiig previous work was above live threshold, causing the high difficulty to bleed into other blocks when genesis open was processed in tests."
    },
    {
      "prediction": "I don't think this is a problem with the `remove_column :products, :discount_title, :string` and `remove_column :products, :discount_title, :string`",
      "reference": "Metrics/LineLength: Line is too long. [89/80]"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please also extend the config tests now to include the new field."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "I think it's wise to keep the behavior backwards-compatible (so `false` as default)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We don't need this line, do we?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't know if we've actually had this problem on Upcase. I'd lean towards having a blank file unless (like on robots) we see multiple errors per week from this crawler."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I'm not good at picking colors, if anyone else has a preference."
    },
    {
      "prediction": "I'm not sure why this is a static method, but I'm not sure why this is a static method.",
      "reference": "Note that even if you cancel the timer, the refreshFolders function might still be running since it's async. Could that be a problem for the test units? One big issue I had with tests is they sometimes would work and sometimes fail randomly, and that's because there are still code running in the background. One example was the ItemChange class, which saves data asynchronously. So I've implemented a waitForAllSaved(), which can be used for test units, to make sure nothing is running once the test ends. So just wondering if we might end up with this issue here."
    },
    {
      "prediction": "I'm not sure why this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "can we make this something more descriptive? like... types should compile? I'm still not sure exactly what this is testing... this says \"Exported types\" - but what does tsd actually look at?"
    },
    {
      "prediction": "I think this is a bug in Android.",
      "reference": "this method is need for full screen video button to appear in players"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this a pointer?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: Space after comma"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "A similar field is already define in `scapy/layers/bluetooth.py`. Can you merge both definitions ?"
    },
    {
      "prediction": "I think this is a hack, but it's a hack, but it's a hack, but I'm not sure if it's a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's a string, so it's not a string, so it's not a string.",
      "reference": "`std::strtok` isn't necessary. The `std::string::find_first_of` is better C++ alternative to `std::strtok`. For example, see `CheckedError Parser::ParseEnumFromString` method."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This property is already declared in a parent with the same visibility/type/value. This one is redundant."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is required, otherwise multiprocessing will (for some reason) crash"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please put in a separate line-separated block"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should error be eaten? If so, not clear why"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `self.on_collection` and `self.force_empty_list`?",
      "reference": "This attribute is not defined if the condition is not met. Instead, you could define another RouteFactory (e.g. `BucketRouteFactory` with a class attribute like `allow_empty_list`)"
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "Can we use the existing `InstalledTimestamp` function?"
    },
    {
      "prediction": "I don't think this is the right thing to do here, but I don't think it's the right thing to do if there are any invalid fields.",
      "reference": "weird naming: `is` but `fields` (plural or singular ?) . If the method checks if the fragment has an invalid value, then \"hasInvalidValue\" or \"containsInvalidValue\" is fine no ?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Does this mean that `listenbrainz.org/user/iliekcomputers` will start getting 404s?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `add_facet_fq_to_solr` and `add_facetting_to_solr` and `add_solr_fields_to_query`",
      "reference": "Line is too long. [82/80]"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "That's a strange name =)"
    },
    {
      "prediction": "I'm not sure if this is a custom template, but it's not a custom template.",
      "reference": "Thoughts on this? I'm not crazy about the brittleness of this but haven't found a good way to test more generically that a specific (custom) template has been rendered."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Have we reached binding-level agreement on the `subscribe` terminology? My only concern is that it doesn't seem descriptive enough and may be confused with subscribing for notifications."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "would it not be safer to move this condition to the `addLink` method?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this might read better: > some apps need the response headers before starting to stream content with http2, so it's important to explicitly flush the headers to the client before streaming the data."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "What does this return if there is no partition? I think that we should consider adding a struct type that describes this tuple. That way, we can use an empty struct for unpartitioned and a non-empty struct for tasks that are combined by partition. We could also support more combinations, like combining across day partitions by not across bucket partitions or similar."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Also, it might be worth returning this for the above lookup on `kbfsRepoDir` as well, which could happen if someone tries to delete a repo in a TLF that has never had any repos at all."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Can this be `Hidden: true` as we already have a bunch of flags that are printed on `--help` and this seems like an average person should not care about it."
    },
    {
      "prediction": "I don't think this is the default value for the `forceBytecodeInvalidation` option.",
      "reference": "Wouldn't this set $strictVariables = true when Config::get returns false?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "was this meant to be checked in?"
    },
    {
      "prediction": "I don't think this is the default.",
      "reference": "check spaces after const name..."
    },
    {
      "prediction": "I don't think this is the case for the NvidiaGPUManager.DriverVersion field.",
      "reference": "If the GPU setting is enabled, resourceFields.NvidiaGPUManager will be nil, right?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We should probably verify that it's readable too"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "See, here's an example where you removed the variable but kept the call, which makes sense."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Please use `request.getTitle()` instead of `feed.getHumanReadableIdentifier()`: In this case, `feed` does not have a human readable title yet"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think the wording on the left is better"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please update the method described to point out that it maintains a chain of interceptors and they will be called in the same order passed in the options."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Is this case purely hypothetical or did it solve an issue that occurred in your testing? I'm trying to understand this change a little better"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Use instead `convert.Int32ToString` that was added in #762 for this purpose."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "If key is present, tree.put(k,v) needs to return a new instance for Maps and the same instance for Sets. Therefore we currently perform an additional 'contains' check for Sets. A future optimization may add an additional flag `replace` to the backing HAMT.put() / RedBlackTree.insert() methods. Sets set it to replace=false, Maps set it to replace=true. But for now this solution is working for us."
    },
    {
      "prediction": "I'm not sure why this is a bug in pandas.",
      "reference": "This is a regression test for code I found while working on this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm wondering if we need to delete jsonStr and jsonAttr after the json_extract_path_text call to avoid unnecessary heap pressure. Though if json_extract_path_text itself does new's on the same heap, we'd get heap fragmentation. Another approach would be to allocate these on the stack instead, avoiding both concerns: char jsonStr[len1+1]; char jsonAttr[len2+1]; ..."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's not a string.",
      "reference": "Does it come as `str`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This should actually read as the following `for (int i = 0; i < allergens.size(); i++)`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is so useful and safety, I want to propose making AppendBool, AppendInt, etc. all private functions, and forcing us to use AppendValue(j, values.New(false)), etc."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Really, really small nit   I believe there's 3x tabs in here? And should it be just 2x?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Perhaps note that rclone can't do this yet?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You probably don't need to set an empty config here."
    },
    {
      "prediction": "I don't think it's a good idea to use `util.datetime_types` instead of `util.datetime_types`?",
      "reference": "I think you are missing `cftime.DatetimeAllLeap` here. That said, all of these are subclasses of `cftime.datetime`, so I think you could get away with just using `cftime.datetime` here, rather than enumerating all of the different subclasses (since `cftime_types` is only used for instance checks)."
    },
    {
      "prediction": "I don't think this is the correct value for the `PredecessorBlockDeviceCPK` property, but it's not the correct value for the `PredecessorBlockDeviceCPK` property, but it's not the correct value for the `PredecessorBlockDeviceCPK` property.",
      "reference": "don't we need to set this label on pool pods? I don't see them being set"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "can remove, it isn't reachable."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `can_downgrade_instead?` method.",
      "reference": "`expect(cancellation).to be_can_downgrade_instead` would be preferred :rainbow: :rainbow:"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Gross. The OS should timeout writes for completely unresponsive clients to begin with. Long term, the better solution is to enforce a minimum minimum data rate for responses. This might require a way to cancel LibuvAwaitables, but it definitely not OK to immediately kill the socket and any ongoing writes just because the request processing loop completed. You could consider doing that after some kind of timeout, but at that point you might as well just enforce a minimum rate."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If this is not used, we should just delete the line."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Are there other callers to this function. How will they be impacted."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Let's be consistent. The majority of boto code does not use relative imports. Let's just stick to the existing standard of \"from boto.package.subpackage import Thing\"."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Suggestion: specify `arity` for this option."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `show_legend` parameter.",
      "reference": "This is a parameter available for the matplotlib backend IIRC. In which case, it is good to see this support added to the Bokeh backend."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's a string, but it's not a string, but it's not a string, but it's a string, but it's not a string, but it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, not a string.",
      "reference": "trim has performance impact and this is the lowest level library... seems the trim if occurs should happen in the UI or Query controller instead.."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Probably also needed for the `http.client.FOUND` below?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Can you also add this to Compiler.md ?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `onOk` and `onError` arguments.",
      "reference": "!numbers -> numbers"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This description doesn't seem quite right for the longrunning case - `longrunning` isn't an orgname."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "maybe give it a more descriptive name, e.g. `competitiveFilter`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This occurrence of \"master\" is unrelated to master/slave replication. Maybe simply remove the word \"master\" or replace it with \"reference\" but \"primary\" doesn't really make sense."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "BLOCKING: This is a problem. We shouldn't be introducing new dependencies on proofs into actors. The miner has some dependencies that should be removed (#2555). This could be accomplished either by moving `proofs.Mode` to `types.ProofsMode` or by forgoing a new type altogether and replacing it with a boolean. The later would have the additional advantage of reducing the number of types we have to export through ABI. I get why `proofs.Mode` has value as a type over a boolean, but I'm not sure it's worth it here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We probably want to log the fact that a `MessageId` was not present in the response. In addition the `RequestID` from `request.Request` should be included in the message so that the user is aware of the issue."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It feels a bit strange to re-assign that here, as that line itself has no context on why it's reassigned. I'd prefer if we could pass `{ propertyID: webPropertyId }` below instead (that's how we do that elsewhere too). This also applies to other similar re-assignments below - let's rather pass the values within the objects as applicable, since then there is more clear context on why this \"rename\" / \"reassignment\" is necessary (because of an object expecting specific properties)."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `countly.compare.models.js` method.",
      "reference": "remove this in the new pr aswell when moving compare to plugins as discussed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "check varHolder is nullptr is redundant, ExecutionContext ensure"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Make these frozen constants?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `isHtml` argument.",
      "reference": "Please use something like html.escape() to ensure that the text is totally safe to include within html. &lt; is not enough."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "why is a buffered channel larger than 1 needed here? the separate goroutines can just try to write to the channel with a select-default block, and then it is not needed. i find the current implementation a bit convoluted, maybe we could simplify it a bit? not sure why it is needed for example to communicate an empty result. these patterns can be simplified using waitgroups"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "There seem to be more changes in here than I'd expect (mostly `limit: 255` additions)."
    },
    {
      "prediction": "I think this is a bug in OpenTelemetry, but it's a bug in OpenTelemetry, but it's a bug in OpenTelemetry, but it's a bug in OpenTelemetry, but it's a bug in OpenTelemetry, but it's a bug in OpenTelemetry, but it's a bug in OpenTelemetry.",
      "reference": "I'm not sure, but I think it's `Tenant`"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Not sure if it's an issue, but this is a breaking change in a public API. Maybe we should add as an overload without optional parameter instead and delegate the existing call to this one?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "as opposed to exposing the chooser function and increasing our API exposure for the purpose of tests, can we move the HTTP transport config test into this package?"
    },
    {
      "prediction": "I don't think this is a problem with the drmModeObjectSetProperty method.",
      "reference": "This is using the legacy DRM interface. DPMS levels have been removed from the atomic interface IIRC. Should we handle DPMS levels at all?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think this was correct before. The nonce passed in here is the nonce at a block (which is the next nonce not yet used, e.g. 0 if the account was never used, 1 if only the tx with nonce 0 has been sent). So if the in-block nonce is 12, then a transaction with nonce 12 cannot have been included yet."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Please name the file ShareExtension.js, as you import it under this name (also could you convert it to TypeScript please?)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure if we need it, but if we set it, be sure to add `,omitempty`."
    },
    {
      "prediction": "I don't think this is the case for a version negotiation packet.",
      "reference": "It's the whole `PublicHeader` that will change soon, and we should state that here, not in the member functions. If Jana's proposal for a new header is accepted, we might also want to rename the fields here. For example, there won't be a dedicated version flag anymore, so a more appropriate name might be `ContainsVersion` instead of `VersionFlag`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think `element` can stay of type `Character` because `Character` is a final class. The we do not need the cast in the line below."
    },
    {
      "prediction": "I'm not sure if this is an annotation type declaration.",
      "reference": "Not sure, if we should do it the other way round. If you ask be in the middle of the night, whether Interface should return true as \"isInterface\" and what Annotation would return. I'd tell you, Annotations should return false.... I want to say, on first glance, I'd say, it's easier to have \"isInterface\" and \"isAnnotation\" rather than \"isInterface\", \"isAnnotation\" and \"isRegularInterface\"... But I see, we also have \"isRegularClass\".... We still have the possibility to change the semantics of those APIs in PMD 7 *Update:* Or in other words: What is less surprising? That isInterface returns true for annotations or that it returns false?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `request.args.get('query', '')`.",
      "reference": "This will potentially skip package results. Do we really want that?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `cudaErrorCooperativeLaunchTooLarge` option.",
      "reference": "Please remove `HIP_UNSUPPORTED`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "if this is a \"Status\" type then the variable name \"Stats\" (which implies \"statistics\") seems wrong (or at least confusing to me)"
    },
    {
      "prediction": "I don't think this is a bug in Sonm.",
      "reference": "maybe will be better to put it into the default worker's config rather than hardcoding the address?"
    },
    {
      "prediction": "I think this should be a function, but it should be a function.",
      "reference": "It seems like this is not meant to test the option failure, but rather that `raw` can be set. This may be a superfluous test now, and we might want to delete it."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `set_fullscreen` method.",
      "reference": "This is already done by `view_set_fullscreen`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "mmm I followed the convention of this collection. It has Add, Remove, RemoveAll, so All sounds reasonable. Else It would likely be AddPeer, RemovePeer, RemovePeers and Peers."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "_nitpick_ I'm thinking about whether this method should be in the previous commit or not. I know it's not yet used there, but in theory, neither do UUID itself."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "\"break\" is right? You skip the line 768."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Can this use the route helper instead?"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Why is this field exported and others aren't?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "should we rename this like `mongodb_srv_tests.js`?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This should still have a value when there is no page title, e.g. just `__( 'Search Traffic Summary', 'google-site-kit' )`."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Oops.. meant to link to SplitOp here. I'll clean up in my next commit"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Remove these unnecessary imports that you've added."
    },
    {
      "prediction": "I don't think this is the right thing to use.",
      "reference": "That space shouldn't be here :wink: This lead to an exception whenever a page with an error was loaded, e.g. an inexistent host - I just fixed that :smile:"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "It seems this is not the way to fix issue #505."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Please take a look at the docstring of `F.binary_cross_entropy_with_logits`. `weight` should be a tensor that matches the input tensor shape. It is Not the class-aware weight. `pos_weight` should be a vector with a length equal to the number of classes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same here, merge with an existing test."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "@aimanrosli23 Could you help to confirm if you do not revert the change in below commit: SHA-1: 643623147a1feaddd734ddd84604e1d8e9dcebee * MdeModulePkg/SdMmcPciHcDxe: Send SEND_STATUS at lower frequency"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we do this without a breaking API change? What about adding a different name to convert directly to a Schema?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why do we need to pull bluebird in here?"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "If *two* threads successfully download the same project into two different temp dirs, and one of them successfully renames one to its final destination, the `if`on line 102 will be false _in the other thread_, and it would leave its temp dir behind."
    },
    {
      "prediction": "I think this is a bug in h2o_socketpool_target_t.",
      "reference": "I would appreciate it if you could rename `link` to `all_link` so that the roles of the two links (the other is `target_link`) become clearer."
    },
    {
      "prediction": "I think this is a bug in the test case.",
      "reference": "Is there a reason not to use `smi.create_expectedIndex` here (and in other places)? The `smi.create_expectedIndex` function will also check to make sure that you don't accidentally skip or duplicate any indexes. With the goal of avoiding errors in the test. It does mean that you have to be diligent with how the expected indexes are created, which can be annoying too. My logic was that it is better to be annoyed by constraints during development time than to find out some time later that the test didn't do what I thought."
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't know if we even need this parameter."
    },
    {
      "prediction": "This is a hack.",
      "reference": "What is the new result of this file if we keep it the same than before? It's just to picture easily what changed in this MR :) (thinking is hard)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This needs to be synchronous for the timeout to work."
    },
    {
      "prediction": "I don't think this is the right thing to do with the reminder email.",
      "reference": "Can you break this onto multiple lines?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "OK, it looks like all children have bit 4 set, but it doesn't really matter at this split point: just informative, nothing reads it."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Sorry for the very basic question but why do we still have a DNSZone CRD in light of the DNSEndpoint, I don't fully understand the differences."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Looks like loop with overhead. You can: - create SID - test private function `sessionIsUnique()`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "In my opinion, it would be better to have two separate settings. One that stores if sorting is enabled and one that stores the order. That allows to toggle automatic sort without having to re-select the order."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `os.Args`?",
      "reference": "/me can't wait to rename this repo :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: maybe call these `loadCollection()/loadDb()`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Did you consider just do `return Task is an external data dependency and data does not exist (yet?).'`? Less `None`'s and `ifs`."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `render` method, but it's not the right thing to do with the `render` method, but it's not the right thing to do with the `render` method, but it's not the right thing to do with the `render` method, but it's not the right thing to do with the `render` method.",
      "reference": "Some day, we really need to make these toolbars pluggable.."
    },
    {
      "prediction": "I'm not sure if this is a pygment?",
      "reference": "This should be `pygment=False` like in `browsertab.py`"
    },
    {
      "prediction": "I don't think this is a bug in the server.",
      "reference": "Should this be moved down (or up) to under the client lock instead of server lock?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why are we removing this?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "What do you think about using `self.id` ?"
    },
    {
      "prediction": "I think this is a bug in Typha, but it's a bug in Typha, but it's a bug in Typha, but it's a bug in Typha.",
      "reference": "Please log once here at Error level \"Failed to connect to Typha, will retry...\""
    },
    {
      "prediction": "I don't think it's a string literal, but it's not a string literal.",
      "reference": "Can you revert this change? The `VERSION` value will be updated after maintainer determines the version at release."
    },
    {
      "prediction": "I don't think it's a string, but it's a string, but it's not a string, but it's a string, but it's not a string.",
      "reference": "It could be better if we use the up case letter to specify the constant string name. Such as QUALIFIED_SERVICE_NAME_KEY can let the user know it's a constant string."
    },
    {
      "prediction": "I think this is a bug in RSpec.",
      "reference": "This should be `@configuration.failure_exit_code`, we don't want to hard code 1."
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is a variable reference.",
      "reference": "Changed per review in Blockly."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hi @wenyingd . so what's the original dst MAC of the reply packet from kube-proxy?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `exclude-too-few-public-methods` option, but I'm not sure if this is the right thing to do with the `exclude-too-few-public-methods` option. I'm not sure if this is the right thing to do with the `exclude-too-few-public-methods` option.",
      "reference": "Note: I wasn't sure what the right wording would be for this, so I used existing language from elsewhere in the codebase."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Docstring for `platform`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should be called before any `os.Exit` otherwise it could still mess up things."
    },
    {
      "prediction": "I think this is a bit_flag with value (1u << 3)",
      "reference": "shouldn't this be `short` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you please paste the output of `volume list` command which will show capacity of a openebs volume."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'd make this a `throw new NullPointerException(\"metric == null\");` instead"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Include should be order lexicographically."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "We need to pass in the Activity context here, so that LoginActivity is used, and so that LoginActivity can get onActivityResult from the PasscodeActivity. Without this, the application context is used, and we don't get a callback when the passcode is done."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Can you move these to the top please, for consistency with other models - normally we put scopes immediately after the associations at the top of the model. As to names I agree with @gravitystorm that these names may be confusing but I'm not sure the ones I suggested are perfect either so I'm not really sure what's best. The goal of my names was just to separate point which could be ordered (as `ordered`) from those which can't (as `unordered`) but I realise that may not be very clear from the names."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the user preferences?",
      "reference": "Looks like the episode should also not be deleted when repeating"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I feel like goimports would move this import line by the other non-std packages... can you double-check that? Run goimports or set up your editor to run it on save. :+1:"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `options`?",
      "reference": "`options['binary'] = WebDriver::Chrome.path` if set?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: Supported -> Enabled."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Yay! I was too lazy to fix this."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "other declaration of errors (from `typecheck`)"
    },
    {
      "prediction": "I don't think this is a problem with the `github.com/myCompany/myRepo` syntax.",
      "reference": "nit: error starts with capital letter"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "the original code ignores \\Draft and \\Recent, whereas your change will not. what this matters, i'm not sure."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why was this necessary?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `--rerun` or `--rerun` or `--sequentially`?",
      "reference": "Can you also do this for Cover?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "So I tried adding this VU a long time ago, thought it would be this simple of a check, but turns out there were other validation in the way for getting here in `ValidateImageAspectMask` I assume that is what is failing CI here, realized it would require some more refactoring"
    },
    {
      "prediction": "I'm not sure if this is a coalesce_and_sum?",
      "reference": "This method is not needed for postgresql, by default sum function omits null values so we can remove this file"
    },
    {
      "prediction": "I don't think we have libsystemd?",
      "reference": "Can you provide a `--with-systemdsystemgeneratordir` option here? So that I can do unprivileged installs without completely turning off systemd. I can add it as a follow-up PR too."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "`classification` is misspelled"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can you change this to `sampleInitCode`?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I added a startTs information in `TiDagRequest` output. Not really sure if it is useful? @zhexuany"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This prevents margin/border/padding CSS from affecting the width/height (otherwise in Chrome a width and height of 1 would result in a rect size of 5x5)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "prefer to just add this to the `verify_authorized` exception list above since we're already making exceptions."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "was there a reason to not loop over parent classes here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `Ember` module.",
      "reference": "@billybonks Why move `import Ember from 'ember';` to the top?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Everything's so simple (a `ThreeStateWorkflow`) until it isn't :smirk:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't quite understand where the NaNs come from..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "File is not `goimports`-ed"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I wonder if we should look at moving the Python stuff to a plugin and doing this there rather than adding to core plz at this point?"
    },
    {
      "prediction": "I don't know why this is the right thing to do with ansible.add_cli_arg('inventory_file', 'localhost,')",
      "reference": "This is the actual bug fix. I prob should have broken this out into two PRs."
    },
    {
      "prediction": "I think this is a bug in Nethermind.",
      "reference": "I am not sure if we need this, we already have DifficultyBombDelays"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "move to finally - I can see at least one return that would omit it, also any exception and so on"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "remove `genesisConfig.GravityChainStartHeight == 0`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this might kill whole application if `var-dumper` will not be installed. What about two separate file_exists conditions (monorepo/project)?"
    },
    {
      "prediction": "I think this is a bug in cobra.",
      "reference": "Hrm. Maybe this isn't the correct spot to run this? Because it errors if the app type doesn't support settings. But we want to check that before running it."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `pretty_list(rtlst, header, sortBy=0)` and `pretty_list(rtlst, header, sortBy=0)` and `pretty_list(rtlst, header, sortBy=0)` and `pretty_list(rtlst, header, sortBy=0)` and `pretty_list(rtlst, header, sortBy=0)` and `pretty_list(rtlst, header,",
      "reference": "Why are you changing this name ?"
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "as we discussed, maybe it would be better to - [ ] set OVERRIDE_IN_DOCKER=1 in the Dockerfile - [ ] replace the if statement with `os.path.exists(\"/run/.containerenv\")` as @dfangl suggested"
    },
    {
      "prediction": "I'm not sure if this is a function being called in a call node?",
      "reference": "I like this style of doing things better than having super big conditional without explanation. Even though I know this won't be re-used it's nice to have a function if only for clarity."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Our preference here is to either have inline statements e.g. `@group_level -= 1 if @group_level > 0` but stylistically here I think `return @group_level if @group_level == 0` might be nicer. As it stands however our rubocop is picking this up as a fail :("
    },
    {
      "prediction": "I'm not sure if this is the case for Spark3.",
      "reference": "Spark3 Is supported in OSS Iceberg, Do you mean this particular function is not supported in Spark3? If so I think we should have a more clear reason why"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "something about the arbitrary file access part here makes me nervous. Can we keep the `if not path.endswith(\".ipynb\")` check from before here as well? Just imagining a weird attack scenario where somebody somehow uses this to get access to confidental files or something"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I wonder if we should push this and the search_params_logic into the blacklight config."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "don't need this line, since it is not tested here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I wonder if adding this new param in the middle of the param list might screw up some existing code that is depending on the old parameter order. Might be better to add it to the end of the parameter list?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I wonder if this absolute path is gonna affect the build-cache relocatability of these compile tasks??"
    },
    {
      "prediction": "I think this should be a boolean?",
      "reference": "possible bug if `fullResponse` is false"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `PyQt5.QtCore` module.",
      "reference": "nitpick: Please only `import string` here and use `string.ascii_lowercase` - I really like to see what module stuff is coming from without looking at the imports."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "nitpick: the only reason we have a catch for every one of these promises is because the test isn't properly chaining promises (returning them within each `then`). We could reduce the `catch` with `console.dir` to a single instance if that was done"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why do this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For consistency, would it not be best to also replace the first class name? `traceLog('Class ' . static::class . ' has been deprecated, use ' . SystemMediaLibrary::class . ' instead.')`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this should be `EnabledAdminAPI` and the json string should then be `enableAdminAPI`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Noticed some missing imports in manage.py so thought I'd add them"
    },
    {
      "prediction": "I think this is the case where the connection is not in the conntrack table, but it is not in the conntrack table.",
      "reference": "as a future improvement, maybe we should just change `ForAllFlowRecordsDo` so that `updateOrSendFlowRecord` uses a flow record pointer instead of a copy of stored flow record. This whole code is executed with the lock any way."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "I am not sure what GitHub wants to tell me with this icon here :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can we also check for smaller zoom levels returning valid error codes?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `LogHeader1` and `LogHeader2` methods.",
      "reference": "1) These names are not great, doesn't help explain what they do. 2) Instead of methods like this that hard code some number of = and *, why not a method that takes the string, defaults to a char to surround with, and a width? 3) Do we really even need headers like this in the output? Maybe we ditch them."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The autocomplete editor shouldn't change its own behavior, I assume that `autoWrapCol` and `autoWrapRow` options should be set to `false` in handsontable editor."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "out of curiosity, with IPv6 introduced, why there's no change to the expected output of openflow in the test?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: grammar: instruction"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We can revert this to reduce the diff of the PR."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "i think this missed the reconciler to callsite change"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please reuse `getClientConfigPath`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should we use the shared chai-addon.js file here? Actually we should consolidate any `chai.use` calls, I see 20 instances, quick win?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe move _agreedCapabilities and _availableCapabilities from List to SortedSet ? We could order them by code and then by version already."
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "I see the `+1` issue, but we used to check if `o.lss != nil` and we don't anymore, so we are sure that it won't be nil here, right?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "why is the `send` needed?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Is this necessary? If so, we need to update the docstring."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Checking for actionable here instead of grabbing the first pending approval. I tested this with proposal ID 265 on staging."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I made this change because I wasn't getting printouts of the 'result' value when the assert was inlined for some reason. I think it's related to creating new CallbackCheckers maybe?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: the correct name is \"request line\", so let's use the right one here :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should now use `[]`, so it crashes if the var is missing"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "you could use `bpf_map_update_elem` with `BPF_EXIST`"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "thanks for noticing this! But I think we should not have it in this PR."
    },
    {
      "prediction": "I don't think this.nLockTime is the same as this.nLockTime.",
      "reference": "A few things: - This may not serialize because I think the property for the sequence number on an input is `.sequenceNumber`. - There should be tests to cover these statements - Indentation is incorrect (should be two spaces, as similar to the statements above)"
    },
    {
      "prediction": "I don't think `data_format` is a valid `data_format`?",
      "reference": "If this is a base method that could be used by others, should you hardcode 'GCS uploader' here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "just a little thing: let's introduce a `final int bound = length - back.length();` that saves us calculating the bound each time checking the loop condition."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think that this should be a POST method, as it changes the state. Get requests should not change the state. With different method, I would suggest to have the handler under `\"/settlements/{peer}\"` path."
    },
    {
      "prediction": "I don't think this is the same as the L2 predeploy contract, but it's not the same as the L2 predeploy contract.",
      "reference": "This is the default value?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The spaces are actually legitimate here: in python, you: - first import standard library modules (hint: time is one) - then import 3rd party library modules - then import the modules from you project (here kinto). Between each block you need an empty line."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Haha, whoa, I'm not sure how I let that one go by. :)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "FWIW: We have FileUtil.generateOriginalExtension for tabular files but it uses a hardcoded list rather than the properties file."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I would consider extracting this logic in to a helper function to make it a bit more readable, but that's just my opinion."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are all fields beginning with \"Debug\" automatically `;local` ? (I guess so, but just checking.)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `dataloader`?",
      "reference": "We should let this module inherits from the EvalHook supported in MMCV, and only override the `__init__` function by adding the warnings. The other functions can use those in MMCV."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Let's use prepared statements here instead  "
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Just leaving this in one place but thanks so much for re-organising all these imports.  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Ditto, here and below"
    },
    {
      "prediction": "I think this should be a function, but it's not a function.",
      "reference": "Let's move the check outside the `for`-loop so that we don't have to do it for every prop. If we change it to check for `vnode.type === 'string'` we can automatically skip checking text nodes which don't have props  "
    },
    {
      "prediction": "This is a hack.",
      "reference": "Seems like the docstring here should simply be \"Deprecated; use `hooks` instead.\"."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is a good idea.",
      "reference": "It would be nice to have an `attr` in `styles.xml` for this, so we don't need the same `if` statement in multiple places"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "How about `null: false` on these two lines? Also `t.timestamps null: false`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This recommendation isn't very helpful because it isn't clear what \"the metastore\" is. How about this instead: \"To fix this, use an alternative metastore\"."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The `SymbolTable` deals only with symbols, I think we can just call this `isUsed` here."
    },
    {
      "prediction": "I don't think this is the case where we want to use `webdriver.http.CorsClient.isAvailable()`?",
      "reference": "Please hide this behind a flag and add a setter function to the builder."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Just a side-node, no need to change it here: The term \"recent\" might be confusing at a later point in time."
    },
    {
      "prediction": "I'm not sure why this.assertEqual(val1 && val1.getTime(), val2.getTime(), errorMessage, depth + 1);",
      "reference": "When can it be undefined? Wouldn't that be a bug?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "JMX offers normal APIs for this. I don't think you want the glassfish one."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Could you remove `,' at the end?"
    },
    {
      "prediction": "I'm not sure if this is a mocha callback?",
      "reference": "Maybe it would simpler to ignore opt_port if type !== 'number'?"
    },
    {
      "prediction": "I don't think this is a good idea to change the account's SpendingKey to \"re-key\" the account's EffectiveAddr to \"re-key\" the account's SpendingKey.",
      "reference": "do you want to rename the codec tag here too?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "These command names are specific to Chromium-based browsers. Please move to `ChromiumDriverCommand`"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Hm.. should we auto-patch? I am less sure on this yet as `percentile_approx` seems a Spark function and auto-patching it in Koalas seems a bit counterintuitive."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I found domain use in `AllFeedsTest::getAllFeedExportCreationData` and class AllFeedsTest is descendant of `FunctionalTestCase`. I think so we can rewrite this too.."
    },
    {
      "prediction": "I think this is the case where we need to maintain the old job's id in the state backend.",
      "reference": "I am wondering if it is better to consolidate all committer checkpoint states into a single structure, e.g. Pojo class or Avro record which are Flink supported state types for schema evolution."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I assume this is a performance optimization to only check this once when creating the signal filter? While you're at it, maybe make `BLACKLIST` a set instead?"
    },
    {
      "prediction": "I'm not sure if this is a `DatabaseDriverNode`",
      "reference": "Please use async/await and try/catch"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Like I said, this code looks incorrect. Why is it still looking up the attribute? Why is it getting the type from `nested->type.struct_def` instead of `field.nested_flatbuffer`? Are you running `generate_code.sh`, because I think `nested->type.struct_def` would be null?"
    },
    {
      "prediction": "I think this is a bug in VkLayerTest.",
      "reference": "Actually, I'm not sure why lines 1663-1668 are here. Looks like Push descriptors aren't used in the test at all. @ziga-lunarg?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Don't we still want to check it it's a keyword?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "this can just me `link_text` :tomato:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What if the Series contains null values?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Every place you see a change like this, it's because `PhysicalLocation` is now its own object, not an array of `PhysicalLocationComponent` objects. The `Uri` is the key into the `FileInfo` dictionary."
    },
    {
      "prediction": "I think this is a bug in sklearn.mixture. I think it's a bug in sklearn.mixture. I think it's a bug in sklearn.mixture. I think it's a bug in sklearn.mixture. I think it's a bug in sklearn.mixture. I think it's a bug in sklearn.mixture. I think it's a bug in sklearn.mixture. I think it's a bug in",
      "reference": "Like in atss_head"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit : I think it would be better to have the multiplier being calculated along with `pool.numPendingWholeBlocks`, so that we could always multiply the feePerByte with that multiplier. Not only that it would be faster, but it would also have constant time. btw - Correct me if I'm wrong, but with this change, you're practically rolling back your previous change while making it `pool.expFeeFactor` adjustable, right ?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Is there a reason we _wouldn't_ want to do this? A bit of a security hole :grimacing:"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please add a copyright notice to all new files. Is there a tool to check and auto update copyright notices?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "A new translation dump should be made after this change (removing the \"Email\" message)"
    },
    {
      "prediction": "I don't think this is the case where `ariaOwned` is `true` and `ariaOwned` is `false` and `ariaOwned` is `true` and `ariaOwned` is `false` and `ariaOwned` is `true` and `ariaOwned` is `false` and `ariaOwned` is `false` and `ariaOwned` is `false` and `ariaOwned` is `false`",
      "reference": "CI is failing saying `expected [TypeError: null is not an object (evaluating 'implicitNodes(role).map')] to equal null`."
    },
    {
      "prediction": "I'm not sure if this is a component.",
      "reference": "@JoviDeCroock I replaced the refs here with simple assignments."
    },
    {
      "prediction": "This is a hack.",
      "reference": "nit: Could we use VisibleForTesting annotation here?"
    },
    {
      "prediction": "I'm not sure why this is a problem with the `posts_count` field?",
      "reference": "Can we create some post records to assert sort_by"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "is this necessary?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is the purpose of this? It seems like it is used to indicate whether there is a filter on a span. But what filter? Could there eventually be multiple filters per span? Just not understanding."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "using a certain type instead of using string directly."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the same file name.",
      "reference": "fix trailing ,"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I've fixed it for this change but for future reference there's no point doing string substitution for a single value like that - it will just slow things down. Just use `:mlat => trace.latitude` etc instead."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "The form no logger needs validation?"
    },
    {
      "prediction": "I think this should be a `Batch<MetricItem>` instead of a `Batch<MetricItem>` instead of a `Batch<MetricItem>` instead of a `Batch<MetricItem>` instead of a `Batch<MetricItem>` instead of a `Batch<MetricItem>` instead of a `Batch<MetricItem>` instead of a `Batch<MetricItem>` instead of a `Batch<MetricItem>` instead of a `Batch<MetricItem>`",
      "reference": "there'd be more changes in the area, when we implement \"clean-up\" of aggregators if no new updates. (i think we currently send metricitem to exporters with zero as value)"
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Usually we only keep the assertions that are relevant to the specification (ie. the test title). For example, the test on the values of id and details is not properly relevant for the spec _collections are isolated by bucket_. I suggest that you only keep the assertions regarding `details` in dedicated tests similar to `test_unknown_collection_raises_404` from `test_views_records.py`, but for each of bucket, group, collection and record in the other `test_views_` files."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The test sources are ok though, you don't need to remove those changes"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`maxWidth: width * 2,` Potentially, this will be the same as `getImageUrl`: 80px or 500px. I can't verify this - need for normal LiveTV tuner."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Not really related to this issue but should we use fuzzy search here as well (like for apps)?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `--force-qr    ` option.",
      "reference": "isn't the usual capitalization for subcommands force-qr? (don't care too much about it)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do you know how many repos have hit this?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'll be interested to see if our gettext rake tasks will pick up on this text to translate"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `instantSpell` method.",
      "reference": "I think you need to change line 928 value from 6 to 7 too, since now table will have 7 values"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does `f0[::-1, :]` mean all the rows taken in a reverse order?"
    },
    {
      "prediction": "I'm not sure how to do this, but I'm not sure if they need bookstores at all. I'm not sure if they need bookstores at all. I'm not sure if they need bookstores at all. I'm not sure if they need bookstores at all. I'm not sure if they need bookstores at all. I'm not sure if they need bookstores at all. I'm not sure if they need bookstores at all.",
      "reference": "Looks like there are strange characters here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It is better to have a check to ensure the format is valid."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `MethodScopeProvider` and `MethodScopeProvider` and `MethodScopeProvider` and `MethodScopeProvider` methods.",
      "reference": "How about `nextAlreadyDefined` variable name in method signature?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "In older SDK versions the data converter was called 3 times but now it is 2. This is because logic was changed deep in the interceptor chains on when values are serialized and encoded and such. Previously we invoked the data converter on results _even if there was an error_ (and most of the time they were nil). Now we don't do such a thing, resulting in fewer calls."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "formatting... can this import go next to the other sources ones?"
    },
    {
      "prediction": "I don't think this is the default.",
      "reference": "I don't understand why anyone would pass 0? If you don't want to attach to an existing process you just wouldn't pass -attach. I would remove that sentence and make 0 an invalid argument."
    },
    {
      "prediction": "This is a hack.",
      "reference": "This change is responsible for #2775"
    },
    {
      "prediction": "I think this is a bug in Datadog.Trace.Tests.RuntimeMetrics.",
      "reference": "Should we add this to the other \"never\" verification in lines 71-73 above, too?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Fixed this since it no longer needed to be switched from a generator to a list, this was missed when I cleaned up the dataset code in an earlier PR."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is an informational message that allows someone to read the console output and understand how the grid node is configured. Please leave."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `name_facts.name_id` and `name_facts.commit_name_id` and `name_facts.preferred_name_id`?",
      "reference": "Can we convert this to an arel as below ContributorFact .joins(:project).where(projects: { id: project_id}) .where('name_id = ? or name_id in (?)', name_id, AnalysisAlias.select(:preferred_name_id) .joins(:project) .where(commit_name_id: name_id) )"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Does this cause issues if you have lots of load on the machine? Having a global variable for this seems like a bad idea IMO."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We probably don't need to print the msg with e.getMessage(). It will be printed by the logger since we are passing the exception as a parameter."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "Can we get a test with multiple directories as per the initial example?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the status bar.",
      "reference": "I assume this is because you were seeing cases where left was a negative number? When?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "this is undoing recent changes for increased consistency of include file statements. please restore to the original."
    },
    {
      "prediction": "I'm not sure why this is the default, but I'm not sure if this is the default, but I'm not sure if this is the default.",
      "reference": "If these are applied in order, should `LambdaMethoReference` come after `OptionalOrElseMethodInvocation`"
    },
    {
      "prediction": "I don't think this is the right thing to write.",
      "reference": "Why this rename?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `sys.modules.pop(\"__main__\")`. I'm not sure if `sys.modules.pop(\"__main__\")`.",
      "reference": "Why do we do this check here? `sys.version_info` cannot be less than 3.3 as pylint does not support older versions. I think we should avoid popping `__main__` altogether."
    },
    {
      "prediction": "I don't think this is the right thing to do with `--verbose` and `--verbose` and `--verbose`",
      "reference": "This can be removed too."
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "I'm a little worried about the new extra calls to `MakeMdId`, since in most local-server KBFS profiles, hashing is the biggest CPU user, and not re-using the value calculated by the client will result in even more hashing. That said, I understand why you did it this way, and I don't have a concrete suggestion on how to make it better. Just something to keep in mind; plus it might be worth comparing the test speed before and after this change to make sure it didn't slow things down too much."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `wp.i18n` or `wp.map` and `wp.element`",
      "reference": "`lodash` shouldn't be grouped under WordPress dependencies"
    },
    {
      "prediction": "This file is not covered by the GNU General Public License.",
      "reference": "Just curious, but how did you work out that Aleksey Sadovoy, Peter Vgner and Joseph Lee contributed to this file? Did you look at the repository history?"
    },
    {
      "prediction": "I don't think the handle is in-active, so we need to make sure that the handle is in-active.",
      "reference": "You could call OnStopRude() directly here to do the same thing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This TODO and this `sort` depend on how the UI looks like. So I think we should fix the UI before continuing on updating this web API. For example, in case the UI flow is as below, this API will receive a Piped ID and then return just ones belonging to that Piped. - User picks where they want to deploy first (select one Piped and one cloud provider) - Then API will be called to show the list of suggested apps for that Piped and cloud provider - User picks app they want to create"
    },
    {
      "prediction": "I don't know why this is needed.",
      "reference": "This command rolls back the volume data to the specified snapshot. Once the roll back to snapshot is successful, all the data changes made after the snapshot was taken will be post. This command should be used cautiously and only when there is an issue with the current state of the data."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should this be a separate/new functional test?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can these also assert at least the length of arrays returned and ideally contents?"
    },
    {
      "prediction": "I don't think this is the default value for `param_visibilities` and `param_visibilities`",
      "reference": "`hasattr(task, 'param_visibilities')` is more concise with the same effect, but either one works."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I would hedge this a little, maybe `Positional arguments appear to be out of order`. After all, it's just a guess."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "you can directly call show() method from **SnackBarHandler.show(coordinatorLayout, getString(no_account_signed_in)).show();** no need to create an extra object and then call the show method."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "concatHosts may be a better func name to explain this?"
    },
    {
      "prediction": "I'm not sure why this is a function, but I'm not sure why this is a function, but I'm not sure why this is a function.",
      "reference": "A function that returns empty string."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If it's not the root package, or if it is the root package but we don't add the psudo :pleasings rule there, print an error."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "can delete this line"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Will it still be an issue if all the models use the same data set?"
    },
    {
      "prediction": "I don't know how to handle this?",
      "reference": "How does this controller_name method work? Does this method grab the context of the url request? Wouldn't this always result in 'widget'?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Let's get rid of these for the final version and if you get rid of the macro I left last time I'd be more than grateful."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `_deleted` flag.",
      "reference": "Instead of `DELETE_MARK`, how about `IS_DELETED`? I don't think that \"mark\" is clear enough to describe what this is. Similarly, I think the docs should be \"Whether the row has been deleted\". There's no need to include \"delete mark\" because that's identifying something that is not defined (this column is _deleted and \"mark\" is not introduced), and \"or not\" is unnecessary because it is implied by \"whether\"."
    },
    {
      "prediction": "I don't think this is a bug in the compiler.",
      "reference": "Does it make sense to have this very thin wrapper that only calls `create_dependencies`? And maybe having `create_dependencies` return a set would be better than convert here?"
    },
    {
      "prediction": "How to do this?",
      "reference": "How about renaming `escape` to `use_path_normalized` or something to better indicate that it is a selection between `path` and `path_normalized`?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Interface members are always `static final` right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It seems to me that this could be in the runtime_nintendoswitch.go file, or is there a reason to keep it separate?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I was actually looking at this code over the weekend and wondering whether we were trying to link here. I assume it's been cargo culted from something else in the compiler."
    },
    {
      "prediction": "I think this is a hack, but it's not worth it.",
      "reference": "nice extraction of the form for being used at new/edit. We should have more of these"
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "Are the coefficients the actual bug fix?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why are the error code options in a list and not a tuple?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Need alignment with the preceding line."
    },
    {
      "prediction": "I don't think this is the default value, but it's the default value.",
      "reference": "Changing from a static method to a constant is inessential to Type Transactions and has a long reach, adding many unneeded files and diff lines."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "There is one caveat: javaslang.collection.Iterator is Iterable. With Iterator it does not work. Let's revert this line. Does this happen elsewhere, too? I will double-check the code..."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Why change the default value of `is_diff`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think tacking on `,<7` would be a wise precaution in case of future incompatible changes in tenacity."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I don't think is necessary to remove the return type"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Also added this check, since client secret is not used except in the IP bypass scenario."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "That's unrelated, but shouldn't there also be a call to `setInternalWebPropertyID`, making it empty, for this case? Otherwise, when selecting to create a new property, any previous internal web property ID will still be in state, potentially causing problems."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I wonder if we should trigger a PHP error and ensure it ends up in the log?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The `move_topic` action be a `post` request since it changes the state of the object."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we just return a non-nil metadata from `Test`?"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "Noticing this is really just the same as cart_notification_email. Would be nice to be able to view custom templates. I may update this with some set up that will make viewing specific custom emails easily."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with it.",
      "reference": "please don't use wildcard imports"
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function, but it's not a function.",
      "reference": "Should we even fix this test? IMO it should be refactored to check that values are recalculated after `setSourceDataAtCell` and `setSourceDataAtRowProp` calls. This will be the correct way to alter the data since now and we're not testing this use case."
    },
    {
      "prediction": "I don't think why this is needed?",
      "reference": "I'm not sure if this is standard practice, but I would prefer to leave this initialization here, if only to show that such a variable exists in this file (instead of inferring it from the globals). It can also cause weird issues if, for example, `init` isn't run before other methods."
    },
    {
      "prediction": "I think this is a hack, but I think it's a bug in RDKit::MorganFingerprints::getHashedFingerprint, but I think it's a bug in RDKit::MorganFingerprints::getHashedFingerprint, but I think it's a bug in RDKit::MorganFingerprints::getHashedFingerprint is a bug in RDKit::MorganFingerprints::getHashedFingerprint",
      "reference": "This isn't how you throw an exception in C++. I'd suggest you take a look elsewhere in the RDKit C++ codebase and see how ValueError exceptions are thrown. Hint: there's a function called `throw_value_error()` that you may find useful."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Was changing this to a write transaction required?"
    },
    {
      "prediction": "I don't think this is a bit of a hack.",
      "reference": "nit: I think \"They\"?"
    },
    {
      "prediction": "I don't think this is the default value for the validator registry.",
      "reference": "is it a result of some multiplication or some other meaningful number? would be nice to display as a power of something or the mult"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I think this class is a good example of where Payload could significantly improve things. I'm okay with this class as it stands. If you merge this in, I'd like to have a go at refactoring it after introducing Payload."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Just a small tip: I think you don't need to include pytest here. You can run tests using: - `pytest tests/path/to/my/test` under the virtualenv to run a single test. - `pytest tests/` under the virtualenv to run all the tests. - `make tests` to run all the tests for all python versions, like travis do. Hope this helps! :)"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Might be worth sorting the replacement items so this is deterministic."
    },
    {
      "prediction": "I don't think this is the default value for the target namespace.",
      "reference": "Should we set the default `TargetNamespace ` to `chaos-testing`? I noticed that the installation script defaults to chaos-testing."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why was this `Task.Yield` removed? It was added in purpose."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You'll also want to do this below, for the `optionalFieldConfigs`. See `GapicMethodConfig.java:180`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We'd better use \"spaceId\" as variable name here. Because i can't figure out the really type for \"space\" at the first glimpse due to \"auto\" used."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I assume we have a package reference somewhere that pulls down the nuget package?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "But why introduce publish on `accConnsEventSubjNew` subject if we never subscribe on that subject. What is the plan then? Replace subscription on \"old\" with \"new\" at one point? Not sure about all that.."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `fme_token` parameter.",
      "reference": "can we use `nullptr` for consistency?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "strange, for templating\\EngineBundle it was `\\Symfony\\Bundle\\FrameworkBundle\\`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "But if we're on the merge deployment, and the next one is the booted deployment, we'll still be inserting between the merge and booted deployment, right? It seems like we would need e.g. `met_merge` and `met_booted` vars to keep track."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can you put the output of this into data, and list which roles are invalid? Same thing with abstract role. I know that's not strictly part of this PR, but it'd make the messaging about this a bunch better."
    },
    {
      "prediction": "I don't think this is the right thing to do with this, but I don't think this is the right thing to do with this, but I don't think it's the right thing to do with this, but I don't think it's the right thing to do with it.",
      "reference": "rename ibftTwo arg to bft"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should we go ahead and push `agent_is_crawler?` into the `skip_session_tracking?` method?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "How about we raise a warning here and simply change to use self.data_infos = self.load_annotations(self.ann_file)"
    },
    {
      "prediction": "This file is not covered by the GNU General Public License.",
      "reference": "Please remove this line to comply with the standard for copyright headers."
    },
    {
      "prediction": "I don't think we want to use the `MinSealersForFinalization` method, but I don't think we want to use the `MinSealersForFinalization` method, but I don't think we want to use the `MinSealersForFinalization` method, but I don't think we want to use the `MinSealersForFinalization` method.",
      "reference": "seems incorrect - for 5 validators it will tell that 3 is enough to seal and you need 4 2/3 * 5 is 3.3"
    },
    {
      "prediction": "I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future. I'm not sure if this is a bug in the future.",
      "reference": "Nit: please remove unnecessary whitespace changes."
    },
    {
      "prediction": "I'm not sure if this is the case for the `resource` field.",
      "reference": "Is this captured in a test?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is used in o.a.l.sandbox.search.LargeNumHitsTopDocsCollector."
    },
    {
      "prediction": "I don't think we want to use `grad_clip=None` here, but we want to use `grad_clip=dict(max_norm=35, norm_type=2)` instead of `grad_clip=dict(max_norm=35, norm_type=2)` instead of `grad_clip=dict(max_norm=35, norm_type=2)` instead of `grad_clip=dict(max_norm=35,",
      "reference": "We may also do the same for `schedule_2x.py` and `schedule_20e.py`."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `:message_read => false` condition.",
      "reference": "Should foreign key here be something like `diary_entry_id`? Or above, in `diary_entry.rb`, it should be `diary_entry_id`?"
    },
    {
      "prediction": "I think this is a hack, but it's a hack, but it's a hack, but it's a hack, but it's a hack, but it's a hack.",
      "reference": "session is a new term. Should we call more like currentCommandBatch or something else?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Will go fmt before squash."
    },
    {
      "prediction": "I don't think this is the default config.",
      "reference": "Setting this to `true` means that it will always get merged in. The way merging is done here is that if a value is its zero value (`false` for `bool`), the value is considered unchanged. In order for this to work, you'll need to change this to be a `*bool` type instead."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It was decided that blockSignerAddress is not only redundant (use the miner owner public key instead which is already stored), but does not belong in config."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "are we not asking for trouble here by not pinning this? or does 3.* imply all of the draft versions we'd try to validate?"
    },
    {
      "prediction": "I don't think it's a temporary placeholder value, but it's a temporary placeholder value.",
      "reference": "No, we want to compare `tm_py` and `tm_cpp` in this test."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Let me know if we'd rather have this as an env variable."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "question: what is happening here?"
    },
    {
      "prediction": "I think this should be removed.",
      "reference": "\\[Checkstyle\\] ERROR: 'protected' modifier out of order with the JLS suggestions\\."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `require('mongodb-extjson')` instead of `require('mongodb-extjson')` instead of `require('mongodb-extjson')` instead of `process.env.CSFLE_KMS_PROVIDERS`",
      "reference": "Can we use EJSON from bson here? and in doing so avoid bringing in the deprecated `mongodb-extjson` lib `const { EJSON } = require('bson')`"
    },
    {
      "prediction": "I don't think this is the default value for the tick format.",
      "reference": "So this parameter is now deprecated?"
    },
    {
      "prediction": "I think this is a bug in RSEQ.",
      "reference": "Actually, it looks like HAVE_RSEQ is only used to determine whether the rseq.h header is around, which then only determines whether the regression test is built: it does not affect whether the core handles an application using rseq. The core rseq mangling code and all the code in rseq_linux.c is always enabled. I believe the idea is that we want DR built on one machine to work on as many others as possible, rather than requiring a custom build for every variant of kernel feature or whatnot. What is the top-level problem being solved here? If it requires disabling or enabling the core handling rseq, probably a separate option should be put in place and maybe HAVE_RSEQ renamed to make it clearer what its consequences are."
    },
    {
      "prediction": "I don't think this is a problem with the `sync` package.",
      "reference": "I don't see a corresponding call to freeSelectorSet... am I missing something?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a bug in OpenTelemetry.Trace.",
      "reference": "Is this part of spec?"
    },
    {
      "prediction": "I don't think we need to wait for the app to be started.",
      "reference": "Hmm, do we need to do this for Windows too? It won't have this private loader TLS issue but it will run DR code in a separate thread before DR init is fully done which I think violates some assumptions. For Windows we would move this wait from win32/os.c to win32/callback.s intercept_new_thread where it checks whether it's a client thread right before calling dynamo_thread_init. If you do not want to deal with Windows you could bail on my suggestion and leave the issue open (or maybe file a new issue) for Windows, or if you want to put the suggested core/win32/ change in place and your new test passes on Appveyor we could then claim to have fully solved this related issue too for all platforms."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "We can remove this function and use `lambda_function_name(..)` in this file instead."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "nitpick: `ApplicationVersion` could be `AppVersion`. It's smaller but gives the same understanding for purposes of the field."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: maybe prefer `resp = &workflowservice.PollWorkflowTaskQueueResponse{}` over adding another function exit points especially for non-error cases?"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "Do we specifically need to keep the read preference as a symbol for use elsewhere? If not, I think it would be cleaner to just modify the options before caching them in the `client_options` method so that we don't do this check every time. If we do need it a a symbol elsewhere, I'd suggest either putting `return @client if @client` at the top of the method (and changing the assignment below from `||=` to `=`) or moving this within the parenthetical block in the last assignment so that we don't repeat this work."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Since this is for video only, should it be called `preferredVideoMimeType`? If we add it for pictures later, it will likely need to be a different option."
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "That doesn't make sense. LayoutEntry doesn't match the generator concept."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think the customer visible strings should be \"Service\" instead of \"Svc\" to make it obvious to them"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Explain why this property is necessary?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It should accept executions as the input"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this limitation necessary?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `json:\"acme,omitempty\"` and `json:\"ca,omitempty\"` and `json:\"ca,omitempty\"`",
      "reference": ":question: Should there be validation to ensure that only one of these attributes is used?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I would recommend using Psr\\Container\\ContainerInterface here instead of Interop\\Container\\ContainerInterface; both currently work, but the Interop version is deprecated and will eventually be removed, so using the Psr version will save us time in the future."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This would also change back to /var/www/html/docroot if we go that way."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this need to be public? Can't one of the helper functions below pass the data? If it really needs to be public, could it be write-protected?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Thanks. Now that you've improved this we should just init and expose the StorageAPI on the node, like the other.s"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "it will be better if you can provide some examples"
    },
    {
      "prediction": "I'm not sure if this is a static class.",
      "reference": "\"return type\" and \"response type\" have never really been contrasted before, and it's unclear what their meaning is here. Could you clarify?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Import order has been violated here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are you suggesting deleting the concept of message querying from plumbing (sounds like more trouble than its worth) or suggesting deleting the snapshot based implementation?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I recommend using StringSliceVarP to resolve the label flag, like `-l key1=value1,key2=value2`. What do you think?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "@Samuell1 Will assigning the same icons array to all the tabs result in, for example, a primary tab called \"Colours\" and secondary tab called \"Colours\" having the same icon?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "A docstring for this function please."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "heads up @JunTaoLuo"
    },
    {
      "prediction": "I don't think this is the right thing to do with the stackFrame.GetMethod()?.DeclaringType.",
      "reference": ".GetMethod() cannot return null now, correct?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Same thing here, I think the proper fix is elsewhere."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "errno is a global variable that might be set by any system library call. It is dangerous to rely on it except right after the system call where it is set. But in this code, it looks like the library call is buried inside ExpLOBInterfaceSelectCursor. It would be safer if the latter function saved errno after whatever system library call it calls, and returns that as an \"out\" parameter, which this code could then check."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "`hasattr` is kinda terrible; just append extra info in the subclass."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Fair warning, the way that exception block is written won't work in python3 Python 3.2.3 (default, Jun 8 2012, 05:36:09) [GCC 4.7.0 20120507 (Red Hat 4.7.0-5)] on linux2 Type \"help\", \"copyright\", \"credits\" or \"license\" for more information. > > > try: > > > ... raise ValueError(\"foo\") > > > ... except ValueError,e: > > > File \"<stdin>\", line 3 > > > except ValueError, e: > > > ^ > > > SyntaxError: invalid syntax"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "This only updates the metadata and not the actual thing you are trying to solve for the docker hypervisor."
    },
    {
      "prediction": "I don't know if the License is available.",
      "reference": "should this package be internal? don't we want to use it e.g. in go-contrib?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if it's a map[string]int or a pointer to a struct.",
      "reference": "Just curious, why did you make this change?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you handle error cases such as `pd.get_dummies(pdf, prefix={\"A\": \"foo\"})`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Where is this environment variable being set?"
    },
    {
      "prediction": "I'm not sure if this is a child of nn.Module, but it's not a child of nn.Module.",
      "reference": "`module_class ` is already a class and `type(module_class)` always returns `<class 'type'>`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: The lambda can be replaced with a method reference: `SparkOrcWriter::new` I think."
    },
    {
      "prediction": "I don't think it's a real int, but it's not a real int, but it's not a real int.",
      "reference": "It would be nice to have a docstring that says what range of integer-like objects will be accepted, as well as what the int_like argument is meant for."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "How do we manage updates to this view down the road?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We can revert this to reduce the diff of the PR."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "I think we should refactor or drop this test, as it is not testing the points format now, but IndexingChain/FieldsInfos' logic. Maybe we could rename the test `testMergeMissing` and configure the first segment to not have the `id` field at all."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "not sure I follow why all this goes away?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is this `{clipboard}` or `{primary}`, as the deprecation message for `:paste-primary` says?"
    },
    {
      "prediction": "I don't think this is the default value for the flag.",
      "reference": "Human unreadable. IMHO user should input MYST value: 0.0006 @chompomonim, opinions?"
    },
    {
      "prediction": "I think this is not a real table, but it's not a real table.",
      "reference": "May be you could elaborate on why you removed this? I see some of this logic has been moved to ia2Web, but couldn't there be cases outside ia2Web (i.e. UIA) in which case ROLE_TABLEROW and ROLE_TABLECOLUMN are mapped to objects, in which case these objects will be of presentation type content erroneously?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This is not consistent. Either rename the first to `tradePlayerItem` (which is ugly) or the second to `partnerTradeItem` (:+1:)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "is there a reason we don't want to gx this dependency?"
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "I'd suggest to add \"ATI \" and \"Intel(R) \" to this list"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This is using a different lang key, we should switch it to using the new key and remove the old key if it is no longer used."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "shouldn't this work? nodesRegex = regexp.MustCompile(api.SpecNodes + \"=(('[0-9A-Za-z,_-]+')|([0-9A-Za-z_-]+)),?\")"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `before_create` method.",
      "reference": "You mentioned this change was prompted because the `before_create` action was actually a defect. This will be done only for a new record; why is `before_validation`, which will be called repeatedly as accounts get updated and saved, correct whereas `before_create` is not? It looks like one would want to assign and activation code, etc., only once."
    },
    {
      "prediction": "I think this is a bug in Datadog.Trace.",
      "reference": "What's the rationale for a default setting to not use a GlobalSamplingRate of 1? I don't know much about the sampling rate stuff"
    },
    {
      "prediction": "I don't know how to use `cygpath -F 38`/Puppet Labs/Puppet Enterprise/bin` or `cygpath -F 38`/Puppet Labs/Puppet Enterprise/bin` or `cygpath -F 38`/Puppet Labs/Puppet Enterprise/bin` or `cygpath -F 38`/Puppet Labs/Puppet Labs/Puppet Enterprise/bin`",
      "reference": "Don't we know if it's 64 by this point? Do we have to test for the directory on every call, or can't we just split the value based on the platform?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "It's not async"
    },
    {
      "prediction": "I think this should be removed in 2.0.",
      "reference": "Maybe we could add some use of `exporterOptions` in this example, otherwise the proper code would replace this variable name with an underscore?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe would be better to rename it to \"onEveryKey\" or \"fireOnEveryKey\"."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "if we're switching to calling FileDownloadHelper, we can just call that directly from the xhtml (see line 357 for example) and then remove this method completely. This is because the other thing it does is check PrivateURLUser, but the FileDownloadHelper method already does that. (and while we're at it, we can remove the method from FileUtil as this is the only place that method is called)"
    },
    {
      "prediction": "I don't think this is a bug in GapicInterfaceConfig.getMethodConfig(String methodSimpleName, String fullName)",
      "reference": "is `fullName` still required as a parameter?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This informational message is important to users. Please leave."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we want to remove this one? Are we planning to substitute it?"
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "We may create an issue to track this so we don't forget?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This file has the executable bit set."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Improve the formatting of the message `.Infof(\"setting db capacity to: %v\", db.capacity)` There is a space before `:` and this way it is easier to see the formatting."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This lock cannot be released here, as it is protecting m_RTPSParticipants and the participant reference."
    },
    {
      "prediction": "I'm not sure why this.model is the same as this.model.",
      "reference": "we'll need this in `_findAndModify` too"
    },
    {
      "prediction": "I don't think this is the default value for DB_NAME, but it's not the default value for DB_NAME.",
      "reference": "This is the fix for the crash. The function to create the intent to launch this activity requires `dbName`, so it has to be set to `null`. In such cases, the value for `dbName` will be set to `null` and cause issues throughout this activity. This adds a default value if the explicitly assigned value in `null`."
    },
    {
      "prediction": "I don't think this is a problem with the `event_textChange` method.",
      "reference": "Shouldn't we also trigger vision update here, so that if someone has caret highlighting enabled the correct character is highlighted?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `context.getNamer().getLocalPackageName()`.",
      "reference": "Woah, how does this change, which includes semicolons, result in the baseline change? Are the semicolon chars just part of the internal representation of the import type?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can't you just use runnvda.bat here?"
    },
    {
      "prediction": "I don't think this is a problem with the `__GNUC__` and `__LCLINT__`",
      "reference": "these definitions of UNUSED aren't the same as the one you imported, so callers should be fixed (if any)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "is type a free string too?"
    },
    {
      "prediction": "I don't think this is the same as the output of the onnxruntime backend.",
      "reference": "here input could be a normal function or an instance of torch.nn.Module."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `nix-instantiate --eval`?",
      "reference": "Example output: \"19.03.git.a7f4a860d0c\" At some point `nixpkgsVersion` was renamed to `version` since someone may use an old channel we fallback to `nixpkgsVersion` for backwards compatibility."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Class import is therefore redundant I guess :)"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "If parsing fails, don't act as no IP specified. Error out."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "... here the semicolon wanted to run away from the enum ;)"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Note that this is in the context of SolrCloud, so \"secondary\" doesn't apply and should be instead follower"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This one is a query parameter and probably really should be ID and in fact I'm mystified as to how this is working because the controller code definitely wants a number for that parameter so the test framework must be converting it back to an ID as best I can tell."
    },
    {
      "prediction": "I'm not sure if this is a HiveTable, but I'm not sure if this is a HiveTable, but I'm not sure if this is a HiveTable, but I'm not sure if this is a HiveTable.",
      "reference": "Need to ensure this is set to TRU for LOB datatype access too not just for hive ."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You're using the Sphinx docstring style here (maybe because it's the default in PyCharm?). Instead, you should use the NumPy style (that you've also used in other places) to be more consistent with the rest of the project."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Don't really need this since the rest of the method will no-op but it's also safe to return early."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Don't use relative paths. src directory is already on the include search path"
    },
    {
      "prediction": "The .NET Foundation licenses this file to you under the MIT license.",
      "reference": "this file can be removed"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we have test cases that name is null?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "in a separate PR, I'll check for a table that is empty/all-null and skip this function call completely."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "We really, really want to catch _everything_ here. It is safe to leave `azkabanEventReporter` set to null."
    },
    {
      "prediction": "I think this should be the case with `parentDom.lastChild` and `parentDom.lastChild`",
      "reference": "Can't we add the check here?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "body is being used here for the first time without every being populated. This will error. To run tests do `./go clean test_py` and that will run the Firefox tests"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Tell me if you have a better field name for this."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "FYI, I have a branch I started to improve this. Nuke can read the target frameworks from the project files, so we don't have to do this mess. Ran into some other issues so it didn't take priority"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is just `mol->atomNeightors()`, is it?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This alias is just for a single occurrence. Maybe it ins't necessary?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "You can delete this `NONE` case."
    },
    {
      "prediction": "I think this is a bug in VkLayerTest, but I think it's a bug in VkLayerTest.",
      "reference": "@cnorthrop -- here is a test with a name change. Is this going to affect your internal CI?"
    },
    {
      "prediction": "I don't think this is a bug in ChromeDriverCommand, but I don't think it's a bug in ChromeDriverCommand.",
      "reference": "Nit: `Headless` is one word, not two, and so doesn't need camelcasing in this way."
    },
    {
      "prediction": "I don't think this is the default value for `parallel_scheduling_processes` and `parallel_scheduling_processes`",
      "reference": "I think this will cause a warning, can you set the default to zero (`0`)?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "confusing naming. Identity from \"id\" package :/ why we need alias here? (and in other imports)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the keyhint dialog.",
      "reference": "It'd be nice to fix up existing configs with the change - that'd mean adding the option to `RENAMED_OPTIONS` in `config.py` and adding something like `_get_value_transformer({'true': '', 'false': '*'})` to `CHANGED_OPTIONS`. I think I never tried adding an option to both, but it should work."
    },
    {
      "prediction": "I'm not sure why this is the same as `Object.keys(Object.getPrototypeOf(prim)`), but it's not the same as `Object.keys(Object.getPrototypeOf(prim))`.",
      "reference": "Perhaps use the new `.keys()` method here instead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't need this option because plan-preview is comparing between 2 commits, not using the live state."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `step_name` option?",
      "reference": "I'm not sure about putting this in the options. I would see it living in an object and then being queried on through a class - a more object oriented, ruby solution."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "So `Status` returns metrics?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `organization.outside_projects(params[:page] || 1)`",
      "reference": "Can we make a generic method say, `set_infographic_view` and in that method we can check the 4 values (outside_committers, portfolio_projects, outside_projects, affiliated_committers) and check against params[:action] and params[:view] and then trigger the respective method dynamically as it takes the standard argument(s) for all the four methods. What do you think?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why would this be called to copy a non-Date object?"
    },
    {
      "prediction": "I don't think it's a bit of a hack, but I don't think it's a bit of a hack, but I think it's a bit of a hack.",
      "reference": "This alignment issue had not appear because no multiple `Boolmsg`s had been serialized at once."
    },
    {
      "prediction": "I think this is the default value.",
      "reference": "Why are we not implementing a BooleanDefaultFalse struct and replacing all of these config vars that default to false with that? Are \"default false\" config vars not affected by this bug?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Replaced this method with a ruby idiomatic setter."
    },
    {
      "prediction": "This program is free tisoftware.",
      "reference": "wrong place hehe"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `mysqld.sock`?",
      "reference": "Can this be `test -e /var/run/mysqld/mysqld.sock` instead of `ls`? Using `ls` for noninteractive stuff is a recipe for sadness, IMHO. /cc @tianon"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `has_many :approvers` and `has_many :api_tokens` and `has_many :outgoing_delegates`",
      "reference": "Are these `dependent: destroy` attributes intended to implement cascading deletes? I had assumed they were added because of the `paranoia` gem, but since that is no longer part of this PR, are they here as a best practice?"
    },
    {
      "prediction": "I think this is a bug in h2o_tunnel_t, but it's a bug in h2o_tunnel_t, but it's a bug in h2o_tunnel_t, but it's a bug in h2o_tunnel_t.",
      "reference": "This approach would work only if there's a guarantee that the stream does not get freed before `establish_tunnel` is called, even though it _may_ enter CLOSE_WAIT state (at which point `stream->tunnel` is set to NULL). I do not think that assumption holds. Hence the alternate approach."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Did you mean to remove the periods here while newly adding to other locations?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "the check can now be `if newLen < 0`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "If we're going to clean up this package, can we also remove those two `_` imports that appear to serve no purpose? (FWIW, they're also in the manager package too...)"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Won't this leak like a sieve? The caller can't delete this as one is a unique_ptr and one is not."
    },
    {
      "prediction": "I think this is a bug in verdaccio/verdaccio/issues/1359.",
      "reference": "form => from"
    },
    {
      "prediction": "I think this should be a property descriptor, not a property descriptor.",
      "reference": "Ok, we can't switch it now, because the properties are a field of the interface Rule - which makes it public API. Maybe we should remove it here in the (Java) API in 7.0.0? The only API left would be, when using a rule and setting the properties in the ruleset xml. There the type doesn't matter - since the String is then automatically converted into a Pattern."
    },
    {
      "prediction": "I think this is a bug in GapicProductConfig.create, but I think it's a bug in GapicProductConfig.create, but I think it's a bug in GapicProductConfig.create, but I think it's a bug in GapicProductConfig.create, but I think it's a bug in GapicProductConfig.create, but I think it's a bug in GapicProductConfig.create.",
      "reference": "Pass in null here, instead of a value? Maaaaybe we should add an overload for `GapicProductConfig.create` that matches the original signature and passes through null? I don't feel strongly about that though, so happy to leave asis if you prefer."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Include all compounds parts from the very beginning for the case check to work later"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "if the user specifies a url scheme on the cli this is going to cause problems, no?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "How about that `scaleFactor`?"
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "`assert(is_int($result));` would be preferable I think, even if we know it can't ever be false"
    },
    {
      "prediction": "I'm not sure if this is a list of items. I'm not sure if this is a list of items. I'm not sure if this is a list of items. I'm not sure if this is a list of items. I'm not sure if this is a list of items. I'm not sure if this is a list of items. I'm not sure if this is a list of items. I'm not sure if this is a list of items.",
      "reference": "I'm unfortunately unable to review whether you've changed everything that used to use cartIds"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the appcompat.app.AlertDialog.",
      "reference": "Please don't touch unrelated files to keep the git history clean"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Per our style guide, I don't think we indent `private` keyword. Would you mind fixing that?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Will this change the input `heatmap`? Is this behavior expected or not?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If I'm reading this right, this changes the parameter name so it'd constitute a breaking change :cold_sweat: Are we missing a test that should have been failing up until now?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Need copyright/license info."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Is this `info log` necessary? If it is not useful, can you consider deleting it?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Unrelated change, but seems to be the correct purpose of the test."
    },
    {
      "prediction": "I'm not sure if this is a plugin.",
      "reference": "Should it be `'uppy-input-`?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "what's the reasoning to keep these always true or dead-code blocks?"
    },
    {
      "prediction": "I'm not sure if this is the first tab button.",
      "reference": "It would be a good practice to do `.off('click', '.tab-buttons > div').on('click', '.tab-buttons > div', function() {`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I suggest that we rely on `--controllers='*,gateway-shim'` for now, and we can then move from `--controllers='*,gateway-shim'` to automatically enabling the Gateway API support on startup using the discovery API in 1.6 or 1.7, what do you think? Note that the logic I wrote in e5436df521015057e77de3fe02c174ea8a863b93 should also use this `GatewaySolverEnabled` flag I think."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "I moved the instantiation of the signature algorithm here, to execute it before the native libraries are configured. Otherwise the wrong signature algorithm could be configured in a future release when more than one is supported in Besu."
    },
    {
      "prediction": "I don't think this is the case for `PyLinter` and `PyLinter`.",
      "reference": "Why remove this?"
    },
    {
      "prediction": "I don't think this is the case where we want to use the `setIeService` method, so we can't use `setIeService` to use the `setIeService` method, so we can use `setIeService` to use the `setIeService` method, so we can't use `setIeService` to use the `setIeService` method, and `setIeService` to use the `setIeService` instead of `setIeService` instead of `setIeService` instead of `setIeService` instead of `setIeService` to use `setIeService` method.",
      "reference": "`this.ieService_` should be initialized to null in the constructor."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not `ebpf::BPF bpf;`? Assuming that the instance is not huge, I do not think there is a good reason to use a pointer when it can be retained as a value."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "nit: move to last block"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: I'm under the impression that `log` is the convention for golang, and that the `er` suffix is usually reserved for interfaces"
    },
    {
      "prediction": "I don't think this is the default behavior.",
      "reference": "Why is IsolationLevel fully qualified? System.Data is already in scope? What do I miss?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "do we still need SanityCheck()? seems they all return nil now"
    },
    {
      "prediction": "I think this is a JSDoc module.",
      "reference": "What I am missing in this PR, and I think we discussed that on the weekly meeting, is that all the code snippets that advise using `loadData` should be changed to one of the two new methods. Otherwise we send confusing mixed signals by promoting `loadData` everywhere in the guides. `loadData` is not deprecated, but is legacy."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Line is too long. [100/80]"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I suggest \"no parent snapshot found, will read all data\\n\"."
    },
    {
      "prediction": "I think this is a bug in NLog.UnitTests.LogFactoryTests and NLog.UnitTests.netfx40.",
      "reference": "`LogManager.ThrowExceptions = true` has very special meaning when unit-testing. Why the change to `LogFactory.ThrowExceptions = true` and enabling after the config-load?"
    },
    {
      "prediction": "I'm not sure if it's a string, but it's not a string, but it's not a string.",
      "reference": "It should be return \"''\"; I will fix it"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is wrong, should be `entry.getValue()`"
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "nit: why can't we combine the two add operations into one so that we add `{\"nameCertificates\": []}` to `/spec/servingCerts` ?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "These whitespace only changes make it very difficult to review this change. Is there any way you could separate just the code changes into one PR and the whitespace only fixes into another? Or are they sufficiently merged together at this point? Chrome is having a real tough time rendering these large diffs."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "why does this suddenly need a config ref"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Unfortunately, I couldn't find a way to get karma to conditionally load stuff from a CDN, so I had to include it."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Those functions are not currently wrapped, so I don't think it is necessary to exclude them (at least for now)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: since this is now a private function rather than a variable, would it make sense to move it after the public functions in this file for readability?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm assuming that MolDraw2Qt drops the alpha channel?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "the code looks good to me, but I just wonder if it is a real use case: (de)serializing a single integer."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Pls remove the print statements. Also, you do not need the if statement."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Thanks for this fix @eltone !   Wondering if we should make this a bit more resilient to upstream changes, e.g., via a regex replacement. Not critical, though - we can pick that up in a follow-up PR.. Thanks"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Should this be instead a configurable option?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "unit test needs an update?"
    },
    {
      "prediction": "I'm not sure if this is the case with the `authProvider` or `authProvider`",
      "reference": "I realised that this is not used anywhere"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "why add the default branch? this may cause there exist multiple configWatchers that notify the eventsCh at the same time?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This line appears to have caused the regression. What is it supposed to be doing?"
    },
    {
      "prediction": "I'm not sure if `attr_value['string'] is not None` and `attr_value['string'] is not None` and `attr_value['string'] is not None` is not required as `attr_value['string'] == value`",
      "reference": "# `attr_value['string'] is not None` probably not required as `attr_value['string'] == value` check is already being done"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@alanwest I noticed this while changing the code. I think we _might_ run into some race condition - if a scraper happens to hit the HTTP server before we could add the reader, what would happen (I guess we will hit exception, which turns into HTTP 500)? I haven't looked into the HTTP server logic. I think it _might_ be OKAY. A better version could be - we only start the HTTP server once the exporter/reader are fully ready and both are hooked up to the provider."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "As for Owin, I think we should exclude this URL in `IsNotServerLifeCheck` too?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does it make sense to just fold these options back into the exporter options? My thinking is that this option is unlike the processor/metric reader options in that it actually is about the exporter itself."
    },
    {
      "prediction": "This is a hack, but it's not a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "here is `:seconds` missing"
    },
    {
      "prediction": "This is a hack.",
      "reference": "change of name is not needed"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hm .. so this case doesn't work anymore?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with QFileSystemWatcher.",
      "reference": "Please indent this so it lines up with the `(`"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `wp_enqueue_script` here.",
      "reference": "We should still register the script. Just not enqueue it."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think this can stay as a method. And we can write our own attribute_change(name) as required."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@alexshikov @Cheesebaron I might be missing something but isn't the viewType parameter here the actual layout resource id? Why would the GetItemLayoutId method need to be called again? On line 127, the exact same method is called except this time passing in the index of the object in the backing data source, which makes sense - the template selector can return the layout id based on the index of the item in the list."
    },
    {
      "prediction": "I don't know why this is the right thing to use.",
      "reference": "Can you change this to use `.format()`?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Maybe the parameter should be consulted higher up the stack so that we only set dropEncap if we're rendering a workload egress chain and the flag is set?"
    },
    {
      "prediction": "I don't think this is a problem with the `VerifyPoSt` method.",
      "reference": "new casing is less ELiTE"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This leaks EGL/GL implementation details into the generic renderer interface."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe add *key* i.e. `\"The \\\\`deploy.on\\\\` key should be a hash (dictionary).`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "its be good also change $code na $id, actual name is misleading and that was probably actual error generator"
    },
    {
      "prediction": "I don't think this is the right thing to do with this.",
      "reference": "I changed the name of the key, to make deployment easier."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "isn't this going to be true by default? if yes, then let's have the env var named `ECS_DISABLE_SPOT_INSTANCE_DRAINING` and have default as false."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do you think we might need this anywhere else in HoloViews?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `session.TranscodingInfo.IsVideoDirect` and `session.TranscodingInfo.IsAudioDirect` and `session.TranscodingInfo.IsAudioDirect`?",
      "reference": "@MrTimscampi don't we want to remove this term entirely? Might as well do it now if that's the case."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I have followed the convention of `cp`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `mysqli::begin_transaction` or `mysqli::begin_transaction` or `mysqli::begin_transaction` and `mysqli::begin_transaction` are the same as `mysqli::begin_transaction` and `mysqli::begin_transaction` and `mysqli::begin_transaction` are the same as `mysqli::begin_transaction` and `mysqli::begin_transaction`",
      "reference": "The docs say it's `false|null`"
    },
    {
      "prediction": "I think this is the default value for the `type` and `trip_time` parameter.",
      "reference": "Thinking on it more, I actually really like your idea to rename `type` to `factor`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This error message is redundant. All of this information is included in the stack trace. In general it's a good idea to avoid using method names in error messages. Chances are the method will be renamed at some point, but the string won't be updated accordingly. Then you'll end up with a very confusing error message. I suggest changing the message to: \"Failed to unblock network loads. Missing INTERNET permission?\""
    },
    {
      "prediction": "I think this is a bug in the NV General Public License.",
      "reference": "Feel free to add your own name while at it."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`signer` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "shouldn't this be `&& opts[:localize]` (i.e. both nil and false skip localization?)"
    },
    {
      "prediction": "I don't think this is a bug in Python 2.6.",
      "reference": "This can also be removed."
    },
    {
      "prediction": "I don't think it's a bug in the future.",
      "reference": "Not critical but \"common\" is not that helpful in the commit title. Maybe go with \"libkvs/txn:\" for this one?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It's been a while, but I just noticed this was wrong: It migrated `True` to `when-searching` (so people with `scrolling.bar = True` suddenly didn't have scrollbars anymore) and `False` to never. Instead, it should migrate `True` to `always` (no behavior change) and `False` to `when-searching` (so people notice the new feature). I fixed this in cc0f5fc6d400e12833ba729049e31d16cf836d53."
    },
    {
      "prediction": "I'm not sure if this is a string, but I'm not sure if it's a unicode string. I'm not sure if it's a unicode string. I'm not sure if it's a unicode string. I'm not sure if it's a unicode string.",
      "reference": ".decode(sys.getfilesystemencoding()) will be better. Although I think rrdtool should accept bytes.."
    },
    {
      "prediction": "I don't know why this is the case.",
      "reference": "An interface call per header might be more expensive than we want to pay. Do we really need this to be abstracted? I think a parser abstraction makes sense, but it seems to me like a separate abstraction for handling headers (one by one) might be an overkill."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Resharper annotations, always +1"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "same here, CryptoSm2 won't be changed once command is compiled"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Loading the login page after the certificate has been loaded. Views can only be loaded from UI thread."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Technically it doesn't belong here; let me remove it."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "remember to update the hash once the upstream PR is merged  "
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Sends the incoming message to the decryptor, which will then forward it to the interface once processing is complete."
    },
    {
      "prediction": "I think this is a bug in the spec.",
      "reference": "FYI This will go the other way, with nil being the correct value for \"no params\""
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "Is this necessary? Are there duplicates in your LibKeyIndex?"
    },
    {
      "prediction": "I think this should be a mock method, but it's not a mock method.",
      "reference": "Why will the gomock files be regenerated? It seems to be irrelevant"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I'm very curious about why using buffered-channel. Is there something wrong to use an unbuffered channel with zero capacity?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the LuigiTestCase, but I'm not sure if this is the right thing to do with the LuigiTestCase.",
      "reference": "It seems like you accidentally pulled some unrelated changes to util_test into this."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with Nethermind.",
      "reference": "do not toucm NDM please - there will be lots of conflicts"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This looks legitimate - Would cause a classCastException. But have we ever seen it in the wild?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This looks out of scope for this particular PR."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Don't need () if only one."
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "Why not have mailPort as int since your are already parsing while calling t.connect ?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `python-daemon<3.0` environment variable.",
      "reference": "In the future, do not remove these trailing commas as they have the purpose of making append-diffs easier to read. :)"
    },
    {
      "prediction": "I'm not sure why this is the first call number.",
      "reference": "Was this added by accident? It doesn't seem related to Syndetics, and I don't think it should be necessary in core VuFind (but maybe it's related to one of your local customizations)."
    },
    {
      "prediction": "I don't think this is a bit of a hack, but I'm not sure if this is the case.",
      "reference": "i know the ergonomics are a little nicer with map[string]bool, but I prefer map[string]struct{} for sets for a few reasons: 1 - optimized storage (not very relevant here) 2 - don't have to think about the conditions where the key exists in the map or if the value could somehow be false"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This is very unclear what Server means. We need a better name, maybe ServerExtension?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I wonder if we should trigger a PHP error and ensure it ends up in the log?"
    },
    {
      "prediction": "I'm not sure why this is a function, but it's not a function. I'm not sure why this is a function.",
      "reference": "Hmmm not sure about this. Is it fine @ar2rsawseen?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why do you prefer `go` over `run`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Unintentional, please remove"
    },
    {
      "prediction": "I don't think this is a problem with the `deactivated_on` attribute.",
      "reference": "What was the reason behind moving this?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Did you mean to put that `join` after the `map` rather than inside it? Also should it be `safe_join` or is interpolating it into an `_html` resource going to have much the same effect>"
    },
    {
      "prediction": "I think this is a realm, but it's not a realm.",
      "reference": "`Indicates if this Realm has been closed.`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "how is this change adding corr to Series? Do all the methods that are added to Frame automatically get added to Series?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just a heads up for anyone else reviewing this, this logic and all the repetitions of it should be greatly simplified by subsequent work relating to issue #2552."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "@billwert I have kept the `1000` InvocationsPerIteration, but do note this is very small for the small types."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the statusbar.",
      "reference": "Unrelated whitespace change."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Slight formatting issue here. There should be a space after the asterisk."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Slight preference for declaring variables inline rather than at the top of the function. That way you can use const for both of these."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this is a duplicate file of the one in demo-schema. please remove this file."
    },
    {
      "prediction": "I think this is a bit of a hack, but I think it's a bit of a hack, but I think it's a bit of a hack.",
      "reference": "Nit: unified names between geth and contracts"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Necessary? Could you just use DefaultBuildState here?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "linked hashmap retains order"
    },
    {
      "prediction": "I think this is a bug in the drm.h.",
      "reference": "And the old names for these variables made more sense imo."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Are you sure this change is correct?"
    },
    {
      "prediction": "I don't think it's a bug in the test_data.path.",
      "reference": "The previously linked bug does not apply anymore? If so, this is LGTM!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why are we renaming all of the tests?"
    },
    {
      "prediction": "I don't think it's a valid nameserver, but it's not a valid nameserver.",
      "reference": "Instead of having this logic, would it make sense to require *users* to encompass the specified IPv6 address within `[` and `]`? Why the magic handling here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not also replace this one with calls to `GetProp<ROMol,T>`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Still need to remove trailing spaces on this line"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please use the `@Experimental` annotation on this"
    },
    {
      "prediction": "I don't think this is the case for a non-io.EOF error.",
      "reference": "I found ~10 more instances of this typo. we can fix those in subsequent PRs."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How about making metricNamespace an option, and by default it's the same as `component`? e.g.m Init(component, WithMetricNamespace(\"trigger\"))"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Just checking: no need for case manipulation?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Same as above, not that descriptive"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "> i#4670 signl-interrupted special ibl xfer frag: Unlink if signal pending nit: This looks like one of many commits with the text before the colon. nit: On the long side: 56 or 60 chars is what some views show Spelling error."
    },
    {
      "prediction": "I think this is a bug in flb_pipe_r, but it's a bug in flb_pipe_r, but it's a bug in flb_pipe_r, but it's a bug in flb_pipe_r, but it's a bug in flb_pipe_r.",
      "reference": "Should we need to invoke pthread_cancel ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is auto generated file so no changes are allowed here"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "All buttons are submit buttons, except if they are `type=reset` or `type=button`. I suggest you do an exclude of those, rather than only include `button[type=submit]`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can you please make this multi line, this version is hard to read."
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function.",
      "reference": "For consistency, it's best to either always use strict equality (`===`) or loose equality (`==`) in `typeof` checks, and to not mix them."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Work Orders would never have only one approver, right?"
    },
    {
      "prediction": "I'm not sure why this is a constant? I'm not sure why this is a constant?",
      "reference": "`code` is written to the message as a `byte`, so I think it's better to declare it in the enum as `byte` as well to avoid a narrowing primitive conversion from `int` to `byte` in runtime."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This is the only \"extra\" change here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please TODO and link to an issue for changing this."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can we make the script output trailing commas?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "This file should get a file header  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "maybe we need process the os error more safely and friendly when open file failed, because this error is very common when cpu has a high pressure, crash directly is danger."
    },
    {
      "prediction": "I don't think this is the best way to do this.",
      "reference": "we need to pay attention not to use this flag everywhere."
    },
    {
      "prediction": "I don't think this is a bug?",
      "reference": "curious about this change, since it is not mentioned in the commit message and now we have `uint8` all over the place"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "wait, are we not mising `WithStamp` here?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "oh. didn't know we store this stage progress."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Going with definition from here: > Does Unicode have private-use characters? > A: Yes. There are three ranges of private-use characters in the standard. The main range in the BMP is U+E000..U+F8FF, containing 6,400 private-use characters. That range is often referred to as the Private Use Area (PUA). But there are also two large ranges of supplementary private-use characters, consisting of most of the code points on Planes 15 and 16: U+F0000..U+FFFFD and U+100000..U+10FFFD. Together those ranges allocate another 131,068 private-use characters. Altogether, then, there are 137,468 private-use characters in Unicode. It looks like we are only ignoring ones in BMP and not the supplementary private-use characters. Shouldn't we consider the supplementary ones too?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "This change is un-tested and requires testing"
    },
    {
      "prediction": "I don't know how to use the `jupyter_bokeh` model?",
      "reference": "Should the docstring mention the vscode option?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "ISTM that since `artman` know the \"real\" value of the GAPIC config name, it should pass that value to toolkit, rather than toolkit guessing the name based on a heuristic. Then again, I don't know what this value actually does for Java codegen..."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please back out the import changes in files you haven't touched. I think these happen if you run goimports without having the vendor directory populated"
    },
    {
      "prediction": "I think this should be removed in 2.0.",
      "reference": "Should this be `ISocketOutput<T> where T : struct`?"
    },
    {
      "prediction": "I'm not sure if this is a snapshot, but it's not a snapshot.",
      "reference": "In which case will this actually return 0? If there is no snapshot, then there is no `Snapshot` object, right?"
    },
    {
      "prediction": "I think this should be a tuple of str, not a tuple of str.",
      "reference": "This part of code is valuable and necessary. Can we move it to another place for a more clear logic and only check it once? For example, move it to line 133 before delving into each module."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Are we at all worried that changing pins will cause release hiccups? I think we've decided that relaxing pins should be safe but adding pins has caused us build issues in the past - so I think we're fine?"
    },
    {
      "prediction": "I don't think this is a bug in the future, but it's a bug in the future.",
      "reference": "could you please explain a bit where these numbers come from? for example: why is there no `swarm.EncryptedSectionSize`?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "s/object content/blob object/ (for consistency with the `Size` docs)"
    },
    {
      "prediction": "I don't think this is a bug in JUnit4, but it's a bug in JUnit4.",
      "reference": "Rather than deleting this entirely, could we just emit it as a `warn` or `info` log line?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is there a chance of this being a BC break of somekind? I.e. what if an old instance of Caddy is running in a cluster with a newer one?"
    },
    {
      "prediction": "I think this should be removed from the temporary store.",
      "reference": "Thanks for this... is this the only place where the rollback is needed? Are there others?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Should this also be a pointer? What happens if there are no BLS messages? I guess that's what this test is exercising, and Lotus also uses a non-pointer here."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "This was definitely a subtle bug right here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "If this method gets all the emails, it should be named appropriately. **all_emails** or just **emails**."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we still random, but if we randomly get a port is used before, we randomly pick again?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I would rather no have this as a `kwarg` as it encourages \"growth\" which lead to an unweildy constructor in other classes. Let's add a method or property to take care of this instead as I think it's usage is going to be quite low."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "what if a purchaser is also an approver? or would that not happen?"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "Not sure why this change. You forgot to handle the case where the user has dynamic fees disabled and there are no fee estimates available. He should be able to sweep none-the-less (as he is using static fees anyway). The line with `config.fee_per_kb()` below, that you have deleted, handled that."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "sorry, I wasn't familiar with this TopLevelCondition... What it would be in this case? The AuditsLogReady condition?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Where does the `alloc` field get set?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "looks expensive to do it on each query"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `nupic.datafiles` file, but it's not the right thing to do with the `extra/nyctaxi/nyc_taxi.csv` file, but it's not the right thing to do with the `nupic.datafiles` file, but it's not the right thing to do with the `nupic.datafiles` file.",
      "reference": "@rhyolight -- but weren't we supposed to be standardizing on using underscores in file names (versus camelcase)?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `_loaded?` and `_added.count + _added.length == 0` and `_unloaded.exists?`",
      "reference": "Can this simply call `in_memory.empty?` ?"
    },
    {
      "prediction": "I don't think we want to do this here.",
      "reference": "The styling/wording here probably needs some thought. It's more of a placeholder."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "Using a plural route helps in detecting the path automatically for `= form_for @password_reset`."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `require('../../../src/utils')` instead of `require('../../../src/utils')` instead of `require('../../../src/utils')` instead of `require('../../../src/utils`)`.",
      "reference": "Is `metadata` required on all tests? I actually just removed the metadata field entirely from a few tests in my PR."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "seems reasonable to also want to include the 'to' location?"
    },
    {
      "prediction": "I don't think this is a good idea to remove the shutdown hook.",
      "reference": "I don't think we need to necessarily check if that returned true or not, we should just remove the shutdown hook. Since nothing would check or do anything with this flag anyways."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Better to push getting policy details into a func we can reuse later."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "optional: while there's nothing to do, a good way to catch bugs (where we use an outbound without calling `Start`) might be to have this outbound verify that `Start` is called before `Call` or `Stop`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Not a blocker by any means, but I think there is value in keeping the local imports in a separate group."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit - I would test the error message as well. For panic, you might need to see if the stack contains the error message, instead of equaling."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Didn't we have specific logic for handling slices vs structs?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "`c_str()` is not needed."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "The handler will be installed twice if you don't remove the below one."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "How about putting `epochLength` (or something like that) in place of `a` just to make it easier to read"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Wouldn't this still fire afterwards if you created one called `pleasings`? or am I missing something?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't love this syntax; it doesn't match anything we're currently doing and it's not obvious. Why isn't this `/keybase/private/jzila,kb_bot/.kbfs_autogit/public/jzila/kbp.git`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Does a type-hint work instead of casting? `return ofAll(toList().<U> zipWith(that, mapper));` (Probably not, just a question.)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Are these required?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is consistent for all clients that we will check yes? Seems like we should just use the singleton, maybe pass it to the parse function or since clients have a server pointer set it at server start and just access that way without locks?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Note that this is a bug, that should be fixed on master. `DECIMAL_LITERAL` cannot match any token, because it's declared with a `#`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `nats-io/nats-server/v2/server/pse`?",
      "reference": "Don't need extra line here."
    },
    {
      "prediction": "I think this should be removed in a future release.",
      "reference": "For the first look, this change is strange. Were we passing these tests before?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea to use `exec.Command(\"taskkill\", \"/pid\", strconv.Itoa(pid), \"/f\")` instead of `exec.Command(\"taskkill\", \"/pid\", strconv.Itoa(pid), \"/f\")`",
      "reference": "On Windows, doesn't `os.Args[0]` include the `.exe`? What if you run the program like `caddy.exe`?"
    },
    {
      "prediction": "I don't think this is the right thing to do here, but I don't think it's the right thing to do here.",
      "reference": "I don't see anywhere where `ServiceConfiguration` interface implementation would return any kind of error. Not sure if its needed, but we could ALWAYS return a valid 'pseudo' configuration without possibility of error."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we actually want to split on `\\r`? I thought that the \"newline sequence\" was only `\\r\\n` on windows."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: these lines are duplicated from above. They can be refactored by setting etype in a conditional and putting 282 and 283 below that."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I would do an s.Notice(\"Initiating Shutdown...\") then after Shutdown() do the original Server Exiting."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Not sure with how many seconds on average are we dealing with but maybe it's better to have hh:mm:ss format in logs - you can make it with `TimeSpan.FromSeconds(seconds).ToString()`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this required? The user should be able to omit it and use the defaults."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `handleInjectedMouseControl` field.",
      "reference": "I don't think the naming of this setting conveys what it does. Maybe something like \"Ignore mouse movement triggered by other applications\""
    },
    {
      "prediction": "I don't think this is the only way to do this, but I don't think it's the only way to do this, but I don't think it's the only way to do this.",
      "reference": "Didn't went with backwards compatibility since it's still in beta"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Perhaps bondsToCut must be None or non empty."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "See above, we could avoid adding that (same applies below)."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `typeMap` property.",
      "reference": "should use Number instead of Long"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should the rest of the file be updated to use `expect` or should this test use the same format as the rest of the tests?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "How would you feel about a different approach where the `DeleteAWSRecordSets` gets passed the zone ID and zone name rather than the `DNSZone`?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "it seems `random.uniform(0, 1)` similar to `random.randint(2)`, all have 1/2 probabilities."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "Added to support EBS volume creation, used like this: blockDeviceMap = [] blockDeviceMap.append( {'DeviceName':'/dev/sdc', 'VirtualName' : 'ephemeral0'}) blockDeviceMap.append( {'DeviceName':'/dev/sdh', 'Ebs': {'VolumeSize' : '100'} })"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "We shouldn't depend that url is `mysterium` - it can be just `testRequestURL`. Also, `URL` has to be upper-case."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We could delay this look-up now and only do it in the non-skip case. I suspect this is true for (almost) all of the top-level refactored functions."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Typically, to be simple, we could reserve a const length space."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Need to add a license and copyright header to each file."
    },
    {
      "prediction": "I'm not sure why this is the right place.",
      "reference": "If I'm not mistaken, this line is now outside of the `if signed_out?` block, right? Any concerns about that? Seems odd that we wouldn't accept coupons for signed in users, but I want to make sure we understand the ramifications of this change."
    },
    {
      "prediction": "I'm not sure if this is a postgrePrivilege, but I'm not sure if this is a postgrePrivilege, but I'm not sure if this is a postgrePrivilege.",
      "reference": "Please remove the unused import of DBPDataSource."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think you should add some extra message here saying it was originally sent as an error, for diagnosability."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe that all the changes in this file are not valid for v1.2 of the Avalon toolkit."
    },
    {
      "prediction": "I don't know why this is the right thing to do with the original role.",
      "reference": "we cannot change the behavior of the processRole - that method is used in lots of places. this call must be done only in the method where templates are being handled."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I think we probably want to follow the same naming convention that we do with `execAgentConfigFileNameTemplate` (using the SHA in the name of the file). This file might be confgurable in the future and when that happens we will be ready. Plus it's pretty much the same code that we already use for the config file."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "If following above, this would be: end_time = time(0) + manual_wall_time_option, which is simpler. Also, make the check manual_wall_time_option > 0, otherwise negative times would terminate the worker right away."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If we aren't using `errors.Is` we don't need the `Unwrap` as we have `Cause` which is what pkg/errors uses."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `beehive/pkg/common/config` or `beehive/pkg/common/log`?",
      "reference": "redundant empty line"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The config.lua.dist still shows `houseAccountOwner`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to use.",
      "reference": "I think we can leave this import and use non FQNs in the code."
    },
    {
      "prediction": "I'm not sure if this is a w3c window, but it's not a w3c window.",
      "reference": "I'd rather just send the parameter twice than break encapsulation here. There's already precedence with webelement IDs"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We should probably exit early if there are no items in the list."
    },
    {
      "prediction": "I'm not sure why this is a test docstring without params?",
      "reference": "As we can't use old names we should warn in whats new for 2.12 that this can happen."
    },
    {
      "prediction": "I'm not sure if this is a test.",
      "reference": "good job finding this package, I hope it's actively maintained"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "same changes as in hipEnvVar.cpp"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `wlr/backend/session.h`?",
      "reference": "NULL check should be before this line"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Seems like client.getlocalplayer is being called a lot, would it be worth it to do final Player player = client.getlocalplayer?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "this change is not correct. 3-valued boolean logic requires that comparison of null to another value during intermediate operations should make the result null and not false. The place where null becomes false is at the very end of that expression. As an example, with the changed logic, this expression will return incorrect result. select * from t where not (a = 1); if a is null, the where predicate will become true which is incorrect. With the original 3-valued result, the where pred will become false and not return any result."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This can already be done with `{>Detected-Locale}`, why make another way to do it?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "These changes just match the logic update in the next method that was done previously - to assure the whole set of files is valid rather than that there is at least one that would be changed."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the flusher.",
      "reference": "Why setting the status to Continue as at the end it is written OK? Status should be written only once."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Howdy! You'll want to do this same thing (replace `hydrateParamCache` with `proofs/bin/paramcache` and then do the copy) in `smartdeps`, too."
    },
    {
      "prediction": "I'm not sure if this command is a snapshot command, but it's not a snapshot command.",
      "reference": "nit : Remove the extra lines"
    },
    {
      "prediction": "The `json:\"dont_listen\"` is a `json:\"dont_listen\"` and `json:\"dont_listen\"` is a `json:\"dont_listen\"` and `json:\"dont_listen\"` is a `json:\"dont_listen\"` and `json:\"dont_listen\"` is a `json:\"dont_listen\"` and `json:\"dont_listen\"` is a `json:\"dont_listen\"`",
      "reference": "Instead of adding a new option, I wonder if we could decide on a port that would disable listening. For instance, port set to 0 means that we use default port 4222. Setting to -1 means that we let OS pick a random free port. We could say anything negative lower than -1 (say -2) means disabled? You don't have to update the PR for that, just wondering if that would be better or not and let's see what others think."
    },
    {
      "prediction": "I don't think it's a bug in clang-tidy.",
      "reference": "Should we add some default case if non of the above return some analyzer name? Something like `unknown analyzer`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nvm. The original version is best... *hides from the angry rubocop*"
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "we can drop this and use the returned body above, right?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it would be better to do it with the `dpl_install_command` command.",
      "reference": "Is echoing enabled on purpose here or it's a remainder of your tests?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `_run_as` option.",
      "reference": "I think this should just be worked into the next message and follow the verbosity of it."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `getServiceAccountSiteURL` in the `getServiceAccountSiteURL` function.",
      "reference": "This also needs to be reverted."
    },
    {
      "prediction": "I don't think this is a bit of a hack.",
      "reference": "`FromCommand` seems to fit better, since with my suggestion below, all pauses will raise a signal on `needPause`. Also maybe the format `journalPauseConflict` and `journalPauseCommand` is better, since the journal isn't necessarily paused yet once we raise a pause signal."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is fix from another PR #120."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `multi` flag.",
      "reference": "I *think* it makes sense to try the more general dictionary (i.e standard python literals) format first. Might be other implications I haven't figured out yet. Then again, ``MultiInterface`` is pretty new so it probably doesn't matter wrt backwards compatibility."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "lol that variable name"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Upper case is reserved for our versions of top-level chains i.e. the `FORWARD` chain jumps to `cali-FORWARD`."
    },
    {
      "prediction": "This is a hack.",
      "reference": "json_handler::receive () has already started a read tx that can be used here right?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We should add the definition to `.storybook/config.js` as well."
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case, but I'm not sure why this is the case.",
      "reference": "I don't believe this is correct. Consider the query, \"select a from t1x where not(b = 0 and c = 0)\". When B and C are both null, both equal predicates evaluate to null, and the AND evaluates to null. The NOT then also evaluates to null. The WHERE clause should treat the result of the NOT as false. But with this fix, the result of the AND will be false, making the NOT true. There needs to be three cases here for ITM_AND: If the first operand is false, then the AND is false. If the first operand is true, then the result is the second operand. If the first operand is null, then if the second operand is false, the result is false otherwise the result is null. Similar logic needs to be added to the ITM_OR case."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "`bound/2` is generally the previous bound that we tested, except when `bound` is equal to 1. It won't break in that case since callers are not supposed to call advance on a target that is lte the current doc ID, but this might still make room for bugs?"
    },
    {
      "prediction": "I think this is the default value for `options.readPreference`",
      "reference": "Can we remove `raw`, `fullResult`, and `serializeFunctions`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "[Nit] I don't have a proposed suggestion, but security seems too generic of a name here."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "do we need to force a buildConfig here? I know it's in muon, but that might actually be making things harder for people"
    },
    {
      "prediction": "I don't think this is the target, but it's not the target.",
      "reference": "Shouldn't need this-> here."
    },
    {
      "prediction": "I'm not sure why this is needed.",
      "reference": "Why delete this?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `ref` and `value`.",
      "reference": "This line is here to be compatible with the current way `refs` work, right?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Hmm, I wonder if we can safely assume all decimals should be displayed as $$...ok for now I suppose."
    },
    {
      "prediction": "I'm not sure if this is a test, but it's not a test.",
      "reference": "Good spec :). Very clear and easy to see what it's doing."
    },
    {
      "prediction": "I don't think this is a problem with the `OrgThirtyDayActivity.most_active_orgs` and `OrgStatsBySector.recent_orgs` and `OrgThirtyDayActivity.most_active_orgs` and `OrgStatsBySector.recent_orgs`",
      "reference": "Shouldn't we need to sanitize the `params[:filter]` from a defined expected values?"
    },
    {
      "prediction": "I'm not sure how to do this with the `describe_tasks` method?",
      "reference": "Should we bite the bullet and poll for the full 5 minutes that AWS recommends? If we do that, we'll probably want to leave some kind of breadcrumb in the event log to let users know why it's taking so long to launch."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Guava changed `Objects` -> `MoreObjects`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "All these hand generated mocks can be deleted. I think we already moved everything to gomocks."
    },
    {
      "prediction": "I'm not sure if this.get('_id') === doc.get('_id')",
      "reference": "what about string/number etc _ids? this will fail."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Looks like the test had a bug prior to this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should start with joplin://x-callback-url/. Also maybe create a helper function to check if a url is valid?"
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case, but I'm not sure why this is the case.",
      "reference": "PR works great. Just out of curiosity: why all the id changes?  "
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "config map first value is wrong, it aims to define the \"value type\", that value will lead to an undefined behavior."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This doesn't make sense. The thing being constructed is a blob.Bucket. \"Constructing\" the pointer is trivial."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Outch. A configuration/parsing refactor is on the radar but this seems more pressing."
    },
    {
      "prediction": "I'm not sure why this is a `Date` object, but it's not a `Date` object.",
      "reference": "Unfortunately this won't work when the \"All time\" range is chosen because `memberStats.days` will be `\"all-time\"` and not a number. What you could do instead is to use `memberStats.stats` as the dependent key and use `Object.keys(memberStats.stats.total_on_date)[0]` to grab the first date in the range and build the label from there."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Style/StringLiterals: Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We need this left in as `axe.configure` is for the top-level page `axe` and we still need to configure the axe script inside the iframe as well (so both have to be configured),"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "is this rule serviceimpacting? I'm thinking it's mostly around the modeling of pageable in the swagger, thoughts?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "same here, replace `ks` and `kc` to something more related to Source."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We should probably ask here if `dict` contains a key with the appropiate value, and leave a trace in case it doesn't, to make it easier to debug for developers."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "this should only be indented 2 spaces"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit, these Err not nils should be `t.Fatalf` not error. We want to the test to stop if this error occurs."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "shouldn't every `Boolean` in this pr be `boolean`?"
    },
    {
      "prediction": "I don't think we want to use `self.execute(Command.W3C_MINIMIZE_WINDOW)` instead of `self.execute(Command.W3C_MINIMIZE_WINDOW`)`.",
      "reference": "This `if` is not necessary"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `System.Threading.Tasks.Task` and `System.Threading.Tasks.Task` and `System.Int32Task` and `System.Threading.Tasks.Task` and `System.Int32Task` and `System.Int32Task` and `System.Int32Task`",
      "reference": "Are you using this anywhere? (I couldn't find it.)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can be inlined"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Please use `kinto.core.utils.json`"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Since we're returning the error with the same content, we don't need to log it here; it will get bubbled up and emitted that way."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "What happens if someone import `typing` and thus uses `@typing.final` instead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Better remove this dependency altogether"
    },
    {
      "prediction": "I think this is a bug in h2o_mem_pool_allocator and h2o_mem_pool_allocator. This is a bug in h2o_mem_pool_allocator.",
      "reference": "Could you please move the declaration to httpclient.h? I think we have a consistent pattern in declaring global variables in header files."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is the case.",
      "reference": "We will also need to add this to the spec."
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack.",
      "reference": "In startEvaluator, we have the paysetHint; we should use it to preinitialize the state delta allocation. The number of transactions and the deltas are typically growing in a linear fashion, so preallocating twice as much in the array initializer would be a good idea."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "we shouldn't add a bunch of static initializers 'everywhere' in the code. Probably just one would be good, during the construction of the 'RemoteWebDriver' class."
    },
    {
      "prediction": "I don't think this should be used in tests.",
      "reference": "Would it be possible to move the creation of the `new { Prop = (object)_value }` out of the benchmark? In the current version, the benchmark includes the cost of creating and serializing the object, while if possible it should be the cost of serialization only."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "only dev and local"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This should not be nullable, instead it should be `->default(0);`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `columns` parameter.",
      "reference": "What about `selectedColumns`? I believe it is frequently used throughout the project."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I thought we switched the approach from a payload to boost attribute? Besides; it's not clear we need this toggle at all since the user could arrange for this behavior simply by having the new DelimitedBoost filter thing in the chain."
    },
    {
      "prediction": "I'm not sure if this is a cisco-5 environment, but it's not a cisco-5 environment, but it's not a cisco-5 environment.",
      "reference": "the previous code used 'export' when platform is cisco-5, presumably because 'env' cannot be used to load variables? I have no idea if that's the case but this env vs export logic is not here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm wondering if we need to add some type of validation here that the SecretCount != 0... Or do we think it would be valid to have a SecretCount of 0?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This test is being skipped. I unskipped it, and it failed in the same way for both `slaveOk: false` and `secondaryOk: false`. I'm not sure how else to test this broken test."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I don't believe that we need a pointer to an interface for the `to` side of this since we're just assigning a value to the to field."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "No blank line after the docstring."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "nit: move this to the group below."
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "This is fine, but maybe we should change the variable name to \"bufferSize_as_uint\"? Or \"...uint32\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Use snake_case for variable names."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Obviously, don't merge this to master."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `expect(reporter).to have_received(:report).with(0)` instead of `expect(reporter).to have_received(:report).with(0)` instead of `expect(reporter).to have_received(:report).with(0)` instead of `expect(reporter).to have_received(:report).with(0)` instead of `expect(reporter).to",
      "reference": "Nearly there! This should assert on the output, take the result of \"start\" and \"finish\" as an example :)"
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "This loop is going to burn CPU if len(s.q) == 0. Maybe a small sleep?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "can you give a reason why session should be contained in RegionManager?"
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "You are comparing two signerIDs here, error message should be \"Signers should match\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Who's acquiring this lock for writes?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This throws a linter error, don't use object creation for side effects. I feel like it's kinda messed up that the errors are thrown by the constructor and not that the constructor will throw them"
    },
    {
      "prediction": "I'm not sure why this is a problem with the `by_topic` method.",
      "reference": "Should there be a `trail.topic_name` method so we don't annoy Demeter?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "instead of passing \"None\" it would be more readable to create a constant e.g. TEAM_PUBLIC = None and then call build_package(TEAM_PUBLIC, ...)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Would it make sense to include this file via composer files-autoloading instead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Each `ExpectedCondition` implements `java.util.Function` These are expected to be stateless. This condition will leak previous `elementText` on the second usage, which doesn't seem ideal."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `testing` package.",
      "reference": "Extra newline here. Thanks for moving it under the `testing` import though. This just needs to be grouped with the other imports below it."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should we ignore case when doing the comparison?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "The same `ifdef` should apply to `#include <wlr/backend/x11.h>` line 14"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "We're instrumenting a static method, so there's no instance in this case. `diagnosticSource` is the first argument."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I feel like this belongs in `RecipientPresenter` (which should really be `MetadataPresenter`), but I suppose having it next to requestReadReceipt makes sense as well. feel free to leave as is."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Let's go back to 1.4.0 until the release is being prepared."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I would avoid the term \"errno\" as it implies the glibc variable. Use error_code or status or something."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@abhinav @kriskowal what do you think about putting the handler on `d`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why `restic.TagLists` and no `restic.TagList` ? Because I'm using `restic.TagList` here and using `restic.TagLists` is a lot of changes"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "An hour seems a significant amount of time to wait for within a test, does it need to be that long?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: (newish to golang, don't hesitate to tell me I'm wrong here, but ...) I'd have written this code, just for readability: keepAlive := false return d.dial(hostName, tlsClientConfig, keepAlive) ... or even return d.dial(hostName, tlsClientConfig, false) // keepAlive=false Personally I think Golang should have included named args; I think it's one of the things python got right."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I don't think it would cause any version conflict, but I'd feel safer if you declared it last, so that the numerical id of the existing integrations don't change"
    },
    {
      "prediction": "I think this is a bug in the API.",
      "reference": "Can we provide some more useful actionable info here? `fmt.Sprintf(\"The certificate request could not be completed due to invalid request options: %s\", req.Status.Conditions[InvalidRequestCondition].Message)`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "yeah, can change to 8545"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "As far as I can see you're not rollbacking transaction anywhere. This could potentially cause further issues(and very hard to debug ones) with not synchronized transactions between message handling. Is the transaction required in this place anyway? You seem only to be fetching data here. ack method is performing some updates so it makes sense"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "What's the meaning of null URIEndpointObject?"
    },
    {
      "prediction": "I don't think this is the default value for `DEFAULT_LOG_LEVEL` and `DEFAULT_LOG_FORMAT`",
      "reference": "Why did you remove the time? It can be useful if some actions are ran in jobs?"
    },
    {
      "prediction": "I'm not sure how to do this, but I'm not sure how to do this?",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "What the reason to change imports?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Nit: continuation indents are 2 indents / 4 spaces."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "You can use `netloc.rsplit(\":\")` for that."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "nits, I don't get the point of this change  "
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`warningPrefix` looks the same on both platforms, we could move it up to `log.go`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "What's the motivation behind switching to plural here? I think we want singular cc @abhinav"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "What do you think about renaming this method `FromErrorAndCode(code Code, err error) *Status`? One of the benefits is that it will be consistent with the naming of `func FromError(err error) *Status {` which does something almost similar."
    },
    {
      "prediction": "This is a hack.",
      "reference": "we cannot state that by default the same value is used if we stopped using null - it would suggest that when you change JSON RPC and leave WS port default then they would be same."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `gexec.Start(command, GinkgoWriter, GinkgoWriter)` and `gexec.Start(command, GinkgoWriter, GinkgoWriter)` and `gexec.Start(command, GinkgoWriter, GinkgoWriter)`",
      "reference": "I'm still not convinced dropping Chrome logs is the right thing to do, but if you insist "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It would be helpful to include some reasoning here. With the reflection model, it is often the case that names are not available."
    },
    {
      "prediction": "I don't think this is a good thing to do here.",
      "reference": "Instead of setting this here, why not have the flag call in the init function set `caddy.LogDestination` directly, and switch on that?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This belongs under \"WordPress dependencies\"."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Was there an issue on `net452`?"
    },
    {
      "prediction": "I think this is a bug in CCI.",
      "reference": "Another option is to always write it without quotes. I always have to use SR. And why not?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `defaultBreakpoints`?",
      "reference": "This should use the `merge` function added in #473 instead of introducing a new dependency"
    },
    {
      "prediction": "I don't think this is a bug in VUID-VkDescriptorUpdateTemplateCreateInfo, but it's a bug in VUID-VkDescriptorUpdateTemplateCreateInfo-templateType-04615.",
      "reference": "Shouldn't this say \"a binding with descriptor type VK_DESCRIPTOR_TYPE_MUTABLE_VALVE\""
    },
    {
      "prediction": "I don't think this is the right thing to do with the `wlr_tablet_tool_v2_grab_interface` and `wlr_tablet_tool_v2_grab_interface` and `wlr_tablet_tool_cursor_surface_role`",
      "reference": "This variable name should probably contain `grab`"
    },
    {
      "prediction": "I don't think this is the default funder.",
      "reference": "Which initializer should we be using for open_aire? The one in `external_apis` or this one in `initializers`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `go-libp2p-peerstore` or `go-libp2p-peerstore` and `go-libp2p-peerstore` and `go-libp2p-peerstore` and `go-libp2p-peerstore` and `go-libp2p-peerstore` and `go-libp2p-peerstore`",
      "reference": "remove todo on line 28?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "clean unnecessary arguments."
    },
    {
      "prediction": "I'm not sure why this is the case for a non-terminal flow.",
      "reference": "Could the name of the status be confusing to users? It says the execution stopped but is it a temporary stop? Will it continue to run at some point? To me the name does not suggest a final status but a transition one. WDYT @sshardool @jakhani @djaiswal83 @aditya1105"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Since we created a Provisioners directory, can we do the same with the tests, and follow the same structure as the code?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `sentryAddr` and `coreAddr` parameters.",
      "reference": "We don't need that one anymore?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Since we're determining the local node's host info in the `Store()` init, we need to import the `STORE` object here. Is this OK, or should I be determining the host info earlier. (When parsing settings?)"
    },
    {
      "prediction": "I'm not sure if this is a cue, but I'm not sure if it's a cue.",
      "reference": "I think, there is no `#getKind()` method anymore, is it? The approach would now be testing with instanceof. Or could we return a more specific type than JavaNode now?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "can we localise these? not sure if we have easy access to a translator instance from `generic-provider-views`"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This is the VID from Adafruit. Doesn't Particle have a different VID? (CC @suda)."
    },
    {
      "prediction": "I don't think we need to do this with the `old_len` parameter.",
      "reference": "The function is only used once, and this body is now only 1 call with the same args (e.g. basically an alias for `vStringTruncate`), it could probably be simply removed. But if you wanna keep the naming for clarity, it also sounds reasonable."
    },
    {
      "prediction": "I think this is a bug in kademlia.",
      "reference": "please change to `could not connect to peer: %s`. it is not relevant to say \"from kademlia\" in a warning"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Why need to remove this? Datetime has microseconds in fact."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "What's up with this, isn't it nil? Why not use the real T value from the test function? @elcore @wmark"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "this feels weird"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't think this is the type of network we should be putting in our named networks."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "debug? I suspect this will be removed before merge?"
    },
    {
      "prediction": "I think this is a bug in MongoClient.connect()",
      "reference": "should this be here twice?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`generate_special` - a meaningless name for me. Can we provide more detailed naming?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "This isn't something you introduced in your changes, but the change makes more obvious to me that this test would be better as a unit test of some kind (probably a controller test). Testing a 404 is an edge case that probably doesn't need to be tested with all components in integration."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We chose `info` in the test code for obvious reasons. Changing to `finest` makes debugging harder and noisier."
    },
    {
      "prediction": "I don't think this should be a string, but it's not a string.",
      "reference": "any reason you're assigning to the local variable 'id' too?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Need to fix this import :)"
    },
    {
      "prediction": "I think this should be a mock.AnythingOfType(\"*types.Block\"), mock.AnythingOfType(\"*types.Address\"), mock.AnythingOfType(\"*types.Address\"), mock.AnythingOfType(\"*types.Address\"), mock.AnythingOfType(\"*types.Address\"), mock.AnythingOfType(\"*types.Address\"), mock.AnythingOfType(\"*types.Address\")).Return(nextStateRoot, nil)",
      "reference": "sorry these tests suck so much we are working to kill them"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Why not adjust `currentTime` to be in ms directly?"
    },
    {
      "prediction": "I don't think this is the case where we need to check if the mcontext base load is the same as the mcontext base load.",
      "reference": "> restore, we find the matching spill for that restore which uses the same slot nit: Two separate sentences: separate with `.` or something besides `,`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "this flag not used"
    },
    {
      "prediction": "I don't think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's a string, but it's not a string, but it's not a string.",
      "reference": "I don't think `?? null` works here... that's to ensure PHP doesn't throw an \"undefined\" error about `$profile->expirationDate`, but now the code is assuming that `$profile->expirationDate` will be set. Might be cleaner to do: <pre> $expiration = isset($profile->expirationDate) ? $this->dateConverter->convertToDisplayDate(\"Y-m-d H:i\", $profile->expirationDate) : null; </pre> And then assigning the `$expiration` value in the return array..."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `app.vue` or `app.vue.config.productionTip`?",
      "reference": "An ENV should be used? Are you sure that the Vue examples are built in the production mode?"
    },
    {
      "prediction": "The `execution_time` field is optional.",
      "reference": "Nit: this should actually always be float since we convert it before we construct the namedtuple."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The result of `FileUtils::fileType` could be saved, instead of calling twice."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Can you log the exception ?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "since this debug message is inside a plugin code, it should use flb_plg_debug(ctx->ins, \"...\"), on this case don't need the component prefix since the API will put it there automatically"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "I also took advantage of the changes to change the Timestamps used in this notification from \"java.sql.Timestamp\" to \"com.yahoo.rdl.Timestamp\"."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "It would be nice all these tweaks to be configurable from cmd line, with sensible defaults"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why do we need this `check_same_thead` to be false? I feel a bit uncomfortable about this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should probably test with constructors which aren't in the schema, and functions which aren't constructors."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "this call doesn't work doesn't? I mean there doesn't seem to be an 2 argument allocate overload. Maybe arg_logical_size should just be defaulted to the arg_alloc_size thing. Or we should just report out physical allocation size instead of logical."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This winds up flipping the desired values. Looks like I gave you a bum steer @kevpl"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: let's call our address ioAddr from now on"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You're killing this \"else\" case here which currently flags an error when maxBoundDescriptorSets == 0."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Nitpick: I'd append `_cb` to the function name here to mark it as a callback. Otherwise it looks a bit like this will do the entire job of removing null checksum refs from a hash table."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "or you can use `filter(x => !x.isView)`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Instead of NewBuffer on the line above, do NewReader to avoid having to wrap later."
    },
    {
      "prediction": "This is a hack.",
      "reference": "No need for this, as pylint already only turns things off for this function and it's needed for the entire function."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "extra brownie points ( overall solution ): we've currently triple-encoding the payset - 1. we encode it to calculate the block size. 2. we encode it to calculate the commit hash ( either via flat, or as Merkle tree ). 3. we encode it as a whole for the purpose of preparing the proposal ( I know that this isn't always the case, but this case happens to be on the critical path ). Caching the encoded data of the *first* block could help us repeating the process."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This assertion should use the actual expanded string, so that it is clear what the message produced looks like. Right now one has to run the code to determine what the message is."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "similar here for imports, these should be consolidated (and also consolidated with the grouping below)"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Maybe there is no need to modify it. Because if you don't use the mask, it won't be initialized."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is there a reason we wouldn't want the trailing `%`? I'm guessing that without the trailing `%` it will just do a strict match vs a partial prefix right?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `fpga_dma.h`?",
      "reference": "Please update the DMA test app in AFU repo once this gets approved."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "There should be a migration for that as well to reflect the change on in-production instances"
    },
    {
      "prediction": "I don't think this is the default AZ options, but I'm not sure if it's the default AZ options.",
      "reference": "Why does it have to be `\"\"` instead of an empty string  "
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This is very strongly opinionated so feel free to disagree with me better, but as conditionals get more complex I like turn them into ifs instead of unlesses. What do you think?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Will this obey the seed set on Kernel?"
    },
    {
      "prediction": "I don't think this is a bug in Puppet.",
      "reference": "We shouldn't use the `&.` syntax here, since we expect that `executor` will never be `nil`. For the functions that _can_ be called from apply / without an executor, `&.` is still appropriate."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why the switch from period to colon?"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string.",
      "reference": "Can you just fix the warning instead? It's actually important for this to have a default of `\"\"` as the subsequent merges with `DefaultConfig()` and `fileConfig()` need to work. If you make this not `\"\"`, you break the assumptions of `Merge()`."
    },
    {
      "prediction": "I don't think this is the default value for `Enabled` and `BaselineTreeMetadataDbCacheIndexAndFilterBlocks`.",
      "reference": "let us not add this"
    },
    {
      "prediction": "I think this is the default value for the `owner_uid` field. I think this is the default value for the `owner_uid` field. I think this is the default value for the `owner_uid` field. I think this is the default value for the `owner_uid` field. I think this is the default value for the `owner_uid` field.",
      "reference": "Is there a need for group as well? crun sets both."
    },
    {
      "prediction": "I think this is a bug in OpenTelemetrySdk.EnableOpenTelemetry",
      "reference": "@cijothomas This build-up pattern was really confusing. It looks like internally ActivityProcessor is intended to be chained but there is nothing in the abstract class that enforces it. We never set a \"Next\" or make sure that the chain is called. Probably need to do some more work in this area?"
    },
    {
      "prediction": "The `pre` method is deprecated, please use `pre` instead of `pre` instead of `findOneAndUpdate` instead of `findOneAndUpdate` instead of `findOneAndUpdate` instead of `findOneAndUpdate` instead of `findOneAndUpdate` instead of `findOneAndUpdate` instead of `findOneAndUpdate`.",
      "reference": "`this.getFilter()` won't work on `pre('save')`. Perhaps make this `toySchema.pre(['updateOne', 'findOneAndUpdate'])`?"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Break out tests for events into their own tests rather than placing them in other ones. That makes it easier for us to figure out where problems lie and to do a TDD-driven implementation over new APIs."
    },
    {
      "prediction": "I don't think this should be done in the future.",
      "reference": "I think this is the only place where we use `UvShutdownReq`. Can we remove the type altogether? Or do you prefer to keep it around?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we can get this to work by passing in the root ca cert fixture that upstream ca is using"
    },
    {
      "prediction": "I don't think the year is correct.",
      "reference": "Just occurred to me to ask: is the condor log date in localtime or UTC?"
    },
    {
      "prediction": "I don't think this is the case where the Mushrooms are empty.",
      "reference": "Can you remove the sculliscep varbits from here too?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I understand that it is a common practice in this script to add indexes this way but why don't we check index existence before adding it? I'm not very familiar with MySql but it's can be done easily in MSSQL and I'm pretty sure that there is a way to do the same here."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "we should probably deprecate (and display a warning) the misspelled keyword arg here rather than removing it... and then add the new one. This changes a public API and will break any code that is currently using the misspelled version."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Should we do something like `h2o__fatal(file, line, \"fatal error: %s, %s\\n\", mess, RSTRING_PTR(...))` here?"
    },
    {
      "prediction": "I think this should be a test, but it's not a test.",
      "reference": "is this one all platforms?"
    },
    {
      "prediction": "I think this is a bug in the jsonhttptest.WithExpectedJSONResponse(jsonhttp.StatusResponse{jsonhttp.StatusNotFound: \"not found\", jsonhttp.StatusNotFound: \"not found\", jsonhttp.StatusNotFound: \"not found\", jsonhttp.StatusNotFound: \"not found\", jsonhttp.StatusNotFound: \"not found\", jsonhttp.StatusNotFound: \"not found\", jsonhttp.StatusNotFound: \"not found\", jsonhttp.Status",
      "reference": "why capitals grr?"
    },
    {
      "prediction": "I think this is a bug in weave.",
      "reference": "Surely all the above should go into `common`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is an unrelated change, but was failing CI... probably introduced in master."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This piece isn't backwards compatible, but it's enough of an edge case that I think it's unlikely to be a problem."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "MB is presumably 1024 * 1024."
    },
    {
      "prediction": "I'm not sure if this is needed.",
      "reference": "Didn't we extract this logic to a `react-features` helper?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "But But, overlapping async writes will get corrupted  "
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `github.com/filecoin-project/go-filecoin/address`?",
      "reference": "Not your immediate problem, but having everything depend on a package that has the config for everything else is ick. Can you move the MessagePoolConfig here and reverse the dependency?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "recently, IME_ACTION_GO action can trigger key_down and key_up event successfully, so we don't need to send enter key separately as before, otherwise will trigger it twice and cause to enter empty passcode, which cause test failed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It seems that you only need to do this `checkExprDepth()` inside `deduceExprType()`. So you don't have to add this check everywhere."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "why split into two lines?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this need to be public or can it be package-private?"
    },
    {
      "prediction": "I'm not sure if this.props.editors.length > 0",
      "reference": " Questionable way of looping through editors and calling `canEditFile` to show the edit button. Is there a better way?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`that is null` doesn't sound very useful to me. Could we rename `that` to `target` or something less context dependent :)?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Just to be consistent, can we use the print function `print()` instead of the keyword. Same goes for line 437."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Having to pass in `price` and `limit` is pretty common. Do we want to have this be another argument, maybe a combined structure that can be used for every action that requires it?"
    },
    {
      "prediction": "I'm not sure if this.item is the same as this.item, but I'm not sure if this.item is the same as this.item.",
      "reference": "Could you move it after `stop`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The variable `method` seems not used. Maybe we can remove the parameter `bodyParamName` and generate it by invoking `ParamUtils.generateBodyParameterName(method)` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think this should be here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Either I'm missing something or specs actors should remove this call cc @anorth"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please undo all these changes as they are white-space only."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You forgot an optimization? `$countries = CountryField::FORMAT_ISO_3166_ALPHA3 === $countryCodeFormat ? Countries::getAlpha3Names() : $countriesAlpha2;`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `py_version` option. I'm not sure if this is the right thing to do with the `py_version` option. I'm not sure if this is the right thing to do with the `py_version` option.",
      "reference": "Shouldn't this also return the current value specified by the user? At least that's what the docstring says and what the previous version did."
    },
    {
      "prediction": "I don't think this is the default value for `time_range`.",
      "reference": "> the time range the listen search the time range of the listen search?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This snprintf, etc. needs to all be inside the DO_ONCE: all this overhead happening on every single decode is likely a huge performance hit."
    },
    {
      "prediction": "I don't know how to do this with `--no_advertise <bool>`?",
      "reference": "would call it connect_retries"
    },
    {
      "prediction": "I think this is a bug in pyspark 3.0.",
      "reference": "Why are we using `repr`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I use the same zms instance to check authentication in swagger endpoints. Same thing in ZTS."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Consider consolidating the common code in a common setup method in tests?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "q: do you need to run the annotation processor over EthProtocolConfiguration prior to writing this file? (i.e.to ensure ImmutableEthProtcolConfiguration exists)? Does Auto-import etc. still work in the IDE?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is the motivation for switching from `Schema` to `DiscoveryField` everywhere?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What happens when ECS Init/whatever's starting the Agent mounts some other directory as Agent's data directory (`-v /tmp:/data`) sets `ECS_HOST_DATA_DIR` to `\"/var/lib/ecs\"` It doesn't seem like a strong enough abstraction to be dependent on Agent configuration options to expect `ECS_HOST_DATA_DIR` to be the same as whatever's being mounted as `/data` on the host. My main concern is the late-binding/asynchronous failures this could lead to if the wrong host mount was specified. Wondering if there are better alternatives here. Can we at the very least inspect the Agent container and check if `ECS_HOST_DATA_DIR` is mounted? If the answer is that we'll revisit the validation here at some latter stage, that's fine too. But, I want us to be aware of potential failures here."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "btw that's obviously out of scope of this PR but since i noticed this line here it reminded me a thing: on some systems i've noticed the font didn't had those characters, so it was just a square or empty space and sometimes they're just a bit shifted in position (if font doesn't have them and using from fallback font which have incompatible dimensions of characters) how do you think is it worth creating an issue to discuss/address it or it could just waste time on bikeshedding?"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core.",
      "reference": "alias is not needed"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do we need to include the path?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "During our zoom and working on this, I said that I believe it was set to 64MB, not 32MB, but the diff shows that I was wrong. So we could change it back to 32MB."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Here I thought you always insisted on ` log \"github.com/Sirupsen/logrus\" ` :) I might do a PR that just globally switches that out wherever we have log."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "We maintain that each (logical) key generation has the same set of device keys, so no need to plumb through `keyGen`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Please use `from unittest import mock` instead of this package."
    },
    {
      "prediction": "I'm not sure if this.options.cursor is set to true.",
      "reference": "Should be `if (this.options && this.options.cursor) {`. Options may be undefined. Also, going forward, mongoose will always use curly braces around if blocks."
    },
    {
      "prediction": "I don't know why this is the default, but I don't know what to do with it.",
      "reference": "This should remain as mailrelay.blackducksoftware.com for staging. Not sure this will be valid, but it shouldn't go through the production mail server."
    },
    {
      "prediction": "I'm not sure if this is a finalizer, but it's not a finalizer.",
      "reference": "Maybe we should have a Debug.Assert for when `Slab != null` to ensure that we are always returning the block (in our tests at least)."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Okay sorry about this I was really confused on how to support uncontrolled in this case, so what we want to do is apply `defaultValue` when `props.value` is falsy but not undefined, right? In the case of us seeing it is controlled (value & onChange present) we apply defaultValue to `props.value` (and delete props.defaultValue) In the case of uncontrolled we shouldn't enter this branch at all and go for full native dom behavior"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "`lodash` shouldn't be grouped under WordPress dependencies"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack.",
      "reference": "The latest yaml in openebs/master has changed to name=admission-webhook. cc: @prateekpandey14"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "using **an** Amazon Simple... Simple Notification **Service** (singular)"
    },
    {
      "prediction": "I think this is a bug in RGroupRows::const_iterator.",
      "reference": "Probably don't intend for this `1 ||` to still be here"
    },
    {
      "prediction": "I don't think this is the case for the `push_descriptor_set` flag.",
      "reference": "Looks like this is failing to compile on Windows (VS 2015 I think)."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit: call the arg something simple like `f` to avoid repeating \"beforeQuery\"."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "do you think this should be `osd/auth` as a pkg to make it more unique and void conflicts with other `auth` packages?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Why are you passing out the Message?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Yikes, this was a bug :grimacing:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I am not sure which one of these is considered idiomatic go... maybe @azdagron has an opinion here? /me prefers the verb since it's shorter. I guess I don't care _too_ much, but it would be good to get some general agreement so we are all following the same conventions"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please check this for error and emit appropriate debugging information. I know this was pre-existing code, but we just have to fix things like this as we go."
    },
    {
      "prediction": "I don't think this is the case for the unreachable condition.",
      "reference": "This seems unrelated, should be a separate PR."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `engine_create_dispatcher.h` and `engine_create_dispatcher.h` and `engine_create_dispatcher.h`",
      "reference": "Never use relative includes, prefer full path"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should fit on the line above without going over the 79-char limit, no?"
    },
    {
      "prediction": "I'm not sure why this is the right thing.",
      "reference": "Is this related to the other contents of this pull request?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Should this be `*string`?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "In the old code here there was no Source Selector, but CreateDefaultProfile will specify a Source Selector of `\"\"`. Is that equivalent?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We should pick this across for all our deprecation specs"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Longer term, I think it could be valuable to move this to cluster-api, and then other repos could take advantage of this as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this a related change?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Given that this is repeated, can we do it outside here and the Create call, what do you think about moving it outside?"
    },
    {
      "prediction": "I'm not sure if this is the first change. I'm not sure if this is the first change. I'm not sure if this is the first change.",
      "reference": "Changing `prop`=>`col` by reference?   I think you can prepare map `prop`=>`col` in L51."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I hate to ask, but can we make this flag shorter so it lines up? :("
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `apis/meta/v1/unstructured` package.",
      "reference": "Note to reviewers: latent, dedup import"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Seems this func is no more needed after your refactoring."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "already added (see several rows below)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "nit: a switch perhaps?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Great you caught this. Super critical to not retry these errors."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Just a little change to make the var effectively final, which is clearer."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Using `\"{}\".format(...)` is a bit beside the point...  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think these should remain as they are."
    },
    {
      "prediction": "I think this is a bug in puppetlabs-sshkeys/master/templates/scripts/manage_root_authorized_keys.",
      "reference": "Let's just call this PERF_PACKAGES and have them in the same format as WINDOWS/SLES/DEBIAN_PACKAGES constants - since it is only a single package and, as written, you'd have to update the code to add more package names anyway. Might as well be consistent with the rest of the code."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "We don't have a `getPluginIDfromTaskIndex` function? I think it should be implemented in Globals/Plugins.h / .cpp"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@shalinmangar If lazy field loading isn't enabled, I don't think this actually changes the behavior of `SolrIndexSearcher`, since it was previously ignoring the fields list anyway. What it _should_ do is allow certain distributed queries, like the ones in `DistribJoinFromCollectionTest`, to co-exist with `SolrIndexSearcher#doc()` respecting the `fields` set instead of just discarding it."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should we be using version 3 now?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Would be better to throw a more specific exception, but for now it will do."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "We should not replace Wei with a type that is shared across multiple units. We need this as `Wei` for type and unit safety."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I'm pretty sure this should emit a util.Warning*(), since we're skipping by here and never hitting anything that will give them a warning about what's happened."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This function isn't useful? it's just a clone of GetParserWithBuiltins?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure if the boolean flags should always contain `is`, also I generally hate too long names... ;) we already know this is a section for circuit breakers, so the name doesn't have to repeat all of it. How about `cpuBreakerEnabled`, `memoryBreakerEnabled` etc?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Before we start the replacing equality deletes with position deletes, I think we need to refactor the RewriteFiles API to adjust more cases: 1. Rewrite data files and remove all the delete rows. The files to delete will be a set of data files and a set of delete files, and the files to add will be a set of data files. 2. Replace equality deletes with position deletes, the files to delete will be a set of equality delete files (we will need to ensure that all delete files are equality delete files ? ) , the files to add will be a set of position delete files. 3. Merging small delete files into a bigger delete files. The files to delete will be a set of equality/position delete files, the files to add will be a set of equality/position delete files."
    },
    {
      "prediction": "I don't think this is the default locale?",
      "reference": "Layout/TrailingWhitespace: Trailing whitespace detected."
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I don't think it's a hack.",
      "reference": "Is it possible that the shortcuts list is empty?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This just changes the error message from `unable to save snapshot: [...] context canceled` to `canceled`."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "maybe it's better to remove HttpHeaders.CONTENT_LENGTH after the loop"
    },
    {
      "prediction": "I'm not sure why this is a list, but I'm not sure why this is a list. I'm not sure if this is a list.",
      "reference": "Very cool. We are now collecting the fruits after your length implementation!"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Is this the same copy of the rules file from above? If so, can just use the copy from above, and this can be dropped."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please break this into multiple lines."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't this new line replace the few lines above?"
    },
    {
      "prediction": "I don't think this is the default value for now.",
      "reference": "Perhaps this belongs in universe?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "there is a `kEpsilon` you can use directly."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This should be grouped with the below imports, and the two separate groups of imports below should likely also be grouped together"
    },
    {
      "prediction": "I think this is a bug in VkDescriptorSetLayout. IsDestroyed()?",
      "reference": "It looks like this error_code field is used to return a string to the caller, not just a const input string to be consumed as in the rest of this PR? If so, my personal preference would be to leave it as a std::string* instead of a reference; I don't know offhand what the VL coding style dictates."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "If return by value, then why bother to make it `static`?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "You'll need to add docs for the argument, see e.g. the `debug_log_filter` docstring above."
    },
    {
      "prediction": "I'm not sure why this is a bug in the future.",
      "reference": "`sdktrace` or `tracesdk`, pick one."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "can we return null instead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You mean XXX and \"we should\" or \"NYI\" or sthg. Maybe put it on the ifdef line."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "minor: can be in-lined in return"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why the additional \"\\n\"?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "This seems to be a big omission. If the first buffer reports an error, stream seems to just discard it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe move this one down too?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We do this in lots of places I'm starting to notice...typically you'd avoid taking concrete dependencies, but we also avoid package dependencies as well which makes sense (i.e. not using an IoC, etc.). Any reason we don't implement some form of poor-man's DI and/or a simple factory instead of new-ing things up everywhere. This may be a simple example (as I'm guessing this is likely the only place this is ever or ever will be used), but separating them doesn't take any more time/effort either really."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "What if formatPrefix doesn't include a space? Will the resulting error have e.Error() stuck at the end without any space?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `pushsync` package.",
      "reference": "that doesn't say a lot to me. Can you please be more specific on the function of pushsync?"
    },
    {
      "prediction": "I don't think this is a bug in VUID-VkGraphicsPipelineCreateInfo-subpass-04890, but it's a bug in VUID-VkGraphicsPipelineCreateInfo-subpass-04890, but it's a bug in VUID-VkGraphicsPipelineCreateInfo-subpass-04890, but it's a bug in VUID-VkGraphicsPipelineCreateInfo-subpass-04890.",
      "reference": "> subpass uses a depth/stencil attachment in renderPass with a read-only layout for the depth aspect Assume - VK_IMAGE_LAYOUT_DEPTH_READ_ONLY_STENCIL_ATTACHMENT_OPTIMAL - VK_IMAGE_LAYOUT_DEPTH_READ_ONLY_OPTIMAL count as well seems there is a `NormalizeDepthImageLayout` for this"
    },
    {
      "prediction": "I don't think this is the right thing to do with this. I don't think this is the right thing to do with this. I don't think this is the right thing to do with this. I don't think this is the right thing to do with this. I don't think this is the right thing to do.",
      "reference": "This shouldn't be altered, you probably meant to update `AREA_PAGE_DASHBOARD_ALL_TRAFFIC` further below :)"
    },
    {
      "prediction": "I'm not sure why this is a hack.",
      "reference": "what does this change do exactly?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What's the purpose of this `backgroundCtx` field?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "non contract incarnation"
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's not a string.",
      "reference": "I would recommend to leave out `None` because None is already the default."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Should the \"bad hello message\" case above also disconnect?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Shouldn't this be in the child and not in the base plugin? Wouldn't having it here enable all derived plugins at once?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should probably say REGEX or PATTERN rather than string."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "I felt we don't need to set it that strict, like if somehow pubsub happens to allow extra 20 bytes for metadata, this test won't work. We would suggest to use 11MB instead."
    },
    {
      "prediction": "I'm not sure if this is the case for many to many associations.",
      "reference": "In theory `isset($metadata['associationType'])` is `false` if the linked field is not an association field, isn't?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@tute the only thing I needed to enable this like as `password` is not in default flow anymore I think."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit: to be consistent with `self.members`, please move this up one line, so that it's closer to `allUsers`? You will need to update your test reference."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `--verbose` option.",
      "reference": "we might as well just access `config.gClientVerbose` directly here. If any other options are passed to `gclientSync` or `gclientRunhooks` then the verbose option will be lost the way it's used now"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Change the key to `default_tab` instead and I'll merge this"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "we still can end up passing a blank org_id to the scope method if for any reason the params is not present..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think yes, this makes sense to expose this. +1"
    },
    {
      "prediction": "I don't think this is the default value for \"hostpath\" in OpenEBS_IO_LOCALPV_HOSTPATH_DIR.",
      "reference": "let us put the sample yaml snippet i.e. maya api server deployment that makes use of this env & value"
    },
    {
      "prediction": "I think this is a bug in ITRabbitMQCollector.",
      "reference": "What changed to cause this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Repeating big interface in many places shows smtg is wrong with design"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `params[:scope]`.",
      "reference": "Inheriting from `AccountsController` to get access to the `redirect_if_disabled` filter."
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "Simple Storage **Service**"
    },
    {
      "prediction": "I think this is the same as `FUNC2(Class<?> arg)`.",
      "reference": "Enter at the end of the file! :-D (and at the end of lines ;-) )"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Don't you want to place this check before you add `succ` to `newSucc`?"
    },
    {
      "prediction": "I don't think this is a bug in this package.",
      "reference": "Commit 676eeeab10884456a5f70ce708a8aa5116ecbaf7 contains a lot of unrelated code style changes. Please get rid of these."
    },
    {
      "prediction": "I don't think this is a bug in the bokeh.io package.",
      "reference": "Well this sucks, I wish you'd mentioned you were using a private API, perhaps we could have made a public one with better guarantees before `0.12.6` was released."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Consider instead moving this into an _test file so it's public but only usable in tests."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Any reason why we want to remove this code ? It helps debugging AWS ebs attach issues. Ideally yes a library should have minimal logging, but there is no way we can track long running AWS attach calls."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "nit: indentation doesn't match (unfortunately i don't know of a way to automatically lint these sql statements with how we're using them currently)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Should we remove the other `setup_profiler` call site and just let this be the one call site for it, since, AFAIK, the other one is no longer necessary with this? Also, can we make `setup_profiler` private?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are there any other templates where this command needs to be added, or were those issues specific to storage requiring us to enable a new command group?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "perhaps file can be removed altogether (trying to avoid an empty package for these build tags)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "NULL change, could you move that out too?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "A brief explanation about this func is required."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `newMergedCell.row`, `newMergedCell.col` and `newMergedCell.row` and `newMergedCell.col` arguments.",
      "reference": "Could you add description for below static function?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since this is only counting the failed attempts, can you call it failedAttemptsCount or retryCount instead of attemptsCount?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I don't think this will work."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since http2 is coming do we want to call this something more specific?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I don't think we want to revert the accessibility issues the tool caught, do we?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I prefer naming this rateLimitedRemoteHost This can be local host but reads remote Host Is Non Local."
    },
    {
      "prediction": "I think this should be a JSX literal?",
      "reference": "Hmm I think I might've messed up this condition here... Need to look more at it"
    },
    {
      "prediction": "I don't think this is a problem with the `package_stats` parameter.",
      "reference": "This also makes the exception to be raised on non-dict falsy values which I think was expected."
    },
    {
      "prediction": "I don't think this is the case where we want to add x-values to the dataset.",
      "reference": "Is this correct? The auto indexing behavior caused problems fixed in a recently merged PR..."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `pysftp=0.2.8` version of the `pysftp=0.2.8` version of the `pysftp=0.2.8` version of the `pysftp=0.2.8` version of the `pysftp=0.2.8` version of the `pysftp` version of the `pysftp` version",
      "reference": "Hmm, didn't we just find out that 1.6 *does NOT* work? We should bump the minimum as well."
    },
    {
      "prediction": "I don't think this is a bug in rai/lib/utility.hpp.",
      "reference": "Will calling `abort()` cause problems for our test suite?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "for my own edificaton, what's this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "make it harmless to commit ws == nil"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `abs_out_exe` and `abs_out_location ([^\\)]+)\\` and `abs_out_location ([^\\)]+)\\` and `abs_out_location ([^\\)]+)\\` and `abs_out_location ([^\\)]+)\\` and `abs_out_location ([^\\)]+)\\` and `abs_out_location ([^\\)]+)\\` and `abs_out_",
      "reference": "Hmmmm, I'm not sure I like these becoming a replacement any build rule has access to. It seems like if it were used in an actual build rule it would only be doing bad things. Can we just use `filepath.Abs` on the returned path in run_step.go?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "That's actually not as bad as I thought it was going to be."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Hmm, I'm surprised if we don't already have a \"find all unpublished datasets\" method but I don't really know. Maybe @scolapasta knows."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The checks in this file are disabled by default since they are meant for Python 3 porting, and this one does not have to do with Python 3 porting at all."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I would change \"should be sent\" to \"must be received\"."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Please put it in following way : `// DeleteStoragePool receives StoragePoolClaim delete event and calls the required handlers to delete other pool related resources.`"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I don't think it's a bit of a hack, but it's a bit of a hack, but I'm not sure if this is the case.",
      "reference": "It's better to use servicecomb now."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Make the flag derived default available in the readiness controller"
    },
    {
      "prediction": "I don't think this is a problem with the `syncset pause` annotation.",
      "reference": "Confirmed this test fails when the fix is reverted "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This method is still possible insecure as it may archive not only logs files. I suggest to filter file names to ensure that they start with `.mysterium-log*`."
    },
    {
      "prediction": "I don't think this is the case for `modulated_deform_conv2dpack` and `modulated_modulated_deform_conv2dpack`",
      "reference": "DCN should not be able to use `init_cfg`."
    },
    {
      "prediction": "Should we throw an exception here?",
      "reference": "It is a bit weird to see a message like \"something must be valid\"."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Again. This is part of the start up of the server, and the diagnostics are helpful."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "I think you need a `,` at the end of the line?"
    },
    {
      "prediction": "I don't think this is a bug in the future. I think this is a bug in the future. I don't think this is a bug in the future. I don't think this is a bug in the future. I don't think it's a bug in the future. I don't think it's a bug in the future. I don't think it's a bug in the future.",
      "reference": "Please avoid wildcard imports."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Did we consider making the timeout an argument to the build task? Would amke it easer to configure in the future: change a build property vs. rebuilding the DLL."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "dumb question: the commit message talks about dual-stack support but it seems that in a dual-stack cluster, Egress will only support the IPv4 address family?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you want to cherry-pick these separately and get them merged already or keep it in here? Both is fine with me!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hmm what are these magical constant numbers? And why does this change mean they should increase?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "This change shouldn't be included with this push. Shouldn't push version changes with a pull-request."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit: let's move this right under where we create the `responseWriter`, before `h.callHandler`"
    },
    {
      "prediction": "This is a hack.",
      "reference": "The way it was implemented, needed to pass the template values. Please check whether we want this."
    },
    {
      "prediction": "I don't think this is the default value for this option.",
      "reference": "Just FYI we need this to align with `builtin.EpochDurationSeconds` from specs-actors or the state machine computations will be off. We'll need to turn this into a config option and follow the same monkey patching paths as the min miner size, seal proof types etc. The EpochDurationSeconds is currently a `const` so can't do it yet tho."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "Is this import needed?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Dashboard stories also need to have the default padding."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Is there a reason why we wouldn't use this as the default?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "if there is an tag of the same name?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I'd add `// +build go1.10` to prevent from accidentally compiling with older Go."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `wrap_tuple` in `get_overlay_spec`?",
      "reference": "Not sure how this import relates to the PR but seems like a good idea anyway..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hmm this is strange, why should the SettingsStruct import something from `WebServer` ? If that's really needed, then we must move stuff as it makes no sense to have some code related to viewing things included in a settings struct. It should be the other way around."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "nit: Space between these lines."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Why aggregator should have this translator? It's Selenium specifics for now..."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I don't understand why this function is needed ? Can't you just pass the information when the `DocComparator` is created in the SortField ?"
    },
    {
      "prediction": "I don't know why this is a problem with Gibbon::MailChimpError.",
      "reference": "This rescue is repeated exactly in `app/jobs/mailchimp_removal_job.rb`. Could we extract a method and pull it up into `MailChimpJob` for reuse?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It's not directly related to this PR, but it would be nice to flow the original error as we're going to print that if the promise is rejected and it'll be more informative than the vague `Network request failed`. Also, I'm not a js dev, so maybe I'm wrong, but throwing a TypeError feels a bit odd."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can we print a debug message when this is used? Since it's a debugging variable, I wouldn't want users to have issues because of a left-over env."
    },
    {
      "prediction": "I think this is a hack, but it seems that the `__examples__/base.jsx` is not a valid `__examples__/icon.jsx` and `__examples__/container.jsx` is not a valid `raw-loader!design-system-react/components/pill/__examples__/listbox.jsx`",
      "reference": "Should we have an avatar, truncate, etc examples, too?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "could you add this to `docs/source/reference/indexing.rst` ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why the change from rdkit.six to six?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Looking good, let's just move this inside the `if` to avoid doing the extra work if we don't need it."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think we should change this to an instanceOf check for MongoBatchReExecutionError"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Required by the libcalico-go changes"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Explain why we don't reuse the corresponding server error locally?"
    },
    {
      "prediction": "I think this is the same as isUnpublishedState, isPublishedState, isPublishedState, isDeaccessionedState, isDeaccessionedState, isUnpublishedState, isPublishedState, isDeaccessionedState, isDeaccessionedState, isUnpublishedState, isPublishedState, isPublishedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isUnpublishedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessionedState, isDeaccessioned",
      "reference": "@JayanthyChengan This change is still missing (and should be last one!): change this line to call getDateToDisplayOnCard(), that way the logic is in only one place (that method)."
    },
    {
      "prediction": "I don't think this is a problem with the API, but it's not a problem with the API, but it's not a problem with the API, but it's not a problem with the API, so it's not a problem with the API.",
      "reference": "What was wrong with more concrete error?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `is_single` and `is_page` and `is_front_page`",
      "reference": "can you replace the tabs with 2 spaces please to match the rest of the project?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why are we adding it to the integral function?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same for this file"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Looks good! But why it's still a out parameter? We can refactor the whole tree because it's internal?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "probably better to use `wlr_seat_keyboard_end_grab()`."
    },
    {
      "prediction": "I think this is a problem?",
      "reference": "Such a large test impact for such a little 3 line change ;)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Is the `cascade` necessary? It should work also without the casdade, because Payments are always already persisted when use cases with them. If it doesn't work, please tell me the reason. It is as same in Transport."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "This is not very short. I'm not sure sure if there's a system for assigning shortcodes to issues."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "We should probably prefix this with `acme-http01` to bring it in-line with other annotations, e.g. `certmanager.k8s.io/acme-http01-edit-in-place`. It's quite wordy, but it *is* more specific (and I'd hope more obvious to the user what it is for?)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "No need to add this file change for this PR. Please remove it."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "this extra dot at the end is causing a couple tests to fail on Travis"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Did you try using `global` with a regular integer ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "windows size might be off"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This should still be guarded with an `#ifdef` since the DataMan code will only be supported for shared lib builds."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `@hash[:attribution].join(', ') %>",
      "reference": "thanks for cleaning up these old length checks  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What will be logged when the `Input.Namespace` was not specified?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `autoFixes` flag, but I don't think it's the right thing to do with the `autoFixes` flag, but I don't think it's the right thing to do with the `autoFixes` flag.",
      "reference": "I wouldn't expose this until the feature is ready. We are most likely to cut releases while still in development"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it would be nice to use `require('css-selector-parser').CssSelectorParser` instead of `require('css-selector-parser').CssSelectorParser` instead of `require('css-selector-parser').CssSelectorParser` instead of `require('css-selector-parser').CssSelectorParser` instead of `require('css-selector-parser').CssSelectorParser`",
      "reference": "I don't think we should pull aria-query into axe-core at this point. There's a much simpler fix for this. Please don't overthink it."
    },
    {
      "prediction": "I don't think this method is called directly, but it's not necessary to call `Slot.Set(this.previousValue);` instead of `Slot.Set(this.previousValue);`",
      "reference": "@ejsmith What if instead of making these two methods public we made it a partial class and moved them to a separate file so that file could be part of the include list? I bring it up just because I don't think it is a very nice API that was ever intended to be public? I think they are only called by a couple of other very internal-y spots. /cc @reyang"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "would be good to turn these into constants."
    },
    {
      "prediction": "I don't think this is a bug in the code generated by gowire. DO NOT EDIT.\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n",
      "reference": "Seems like it should be `generated by Wire` here and in the SUT?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I know the main cases show up in the daemon test already but a little bit more unit test coverage would be nice and probably not too annoying to set up. Ideas: 1. Verify that the string \"no duplicates\" is in the LastDuplicate field when we propose a new deal. 2. Verify that proposing a duplicate deal fails when the duplicates boolean is set false. 3. Start out in a state with more than 1 duplicates. Verify that the LastDuplicate field is set to the last duplicate when we propose with a true duplicates bool."
    },
    {
      "prediction": "Should we throw an exception here?",
      "reference": "`Timeout.Infinite` is actually `-1`. Here the correct message can be taken from Line:67."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with Xunit.",
      "reference": "I think we need `#if !SILVERLIGHT` here and at the test."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can you change this import to the apache dependency? I didn't even know that jgit contains such a method..."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Four strings in a row makes me nervous, can we use an arguments struct instead? Or reuse the struct I recommend in the reconciler."
    },
    {
      "prediction": "If the value is stored as a JSON, then it is stored as a JSON object.",
      "reference": "should work with no options, if my suggestion is accepted. JSON is the one that gets weird since a JSON object appended to a JSON object isn't valid JSON."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I presume this isn't some special term..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Did you mean to return here? ;) You'll also need to add an `incomplete` message to the rule metadata."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "Why are we calling these as annotations? I guess this is an old type that we are re-using. But lets make it a point to avoid once we feel that this design/code is not good."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "`invocation.getInvocationStageTrace().startSend()` is inside `RestClientSender.send`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "use \"actionHash\" to be consistent with other places"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Can we derive `Class<E>` by looking at one of the label choices, if at least one is always provided? Given these are immutable, a real-world case for an empty enumerations eludes me."
    },
    {
      "prediction": "I don't think this is a good idea to use VkExternalFormatANDROID value.",
      "reference": "I am now confused here, the spec says > If format is VK_FORMAT_UNDEFINED, all members of samplerYcbcrConversionComponents must be the identity swizzle. The spec also says > samplerYcbcrConversionComponents is the component swizzle that **should** be used in VkSamplerYcbcrConversionCreateInfo. so you are allowed to set the swizzle to anything I want, so I guess this is valid usage here... but now I am more curious if I have an external format does it not have to follow any component swizzle rules and can be anything regardless of the `ycbcrModel`? (I guess really a question for @critsec and is not a blocking concern for the scope of this PR)"
    },
    {
      "prediction": "I think this is a bug in `ddev start` and `ddev start` and `ddev start` and `ddev start`",
      "reference": "I'd say the error should be an error, not instructions to the user. So error would be something like \"site should be running and is not\""
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "Thanks for this PR @pinzon !   Rather than resetting the `sms_messages` list, can we fix the assertion in line 902 - rather than asserting `len` equality, we should assert that all expected messages are contained in the list. (In this case the phone numbers should be reasonably random, and ideally we should not have duplicates across different tests). We're planning to introduce test parallelization in the near future, and this will help us avoiding undesired side-effects.   Thanks"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Some weird blocks formation again."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is worrisome."
    },
    {
      "prediction": "I'm not sure why this is a problem with the API, but it's not a problem with the API.",
      "reference": "nit try rephrasing to something like \" AutoFilesystemTrimUsage returns the volume usage and trimmable space of locally mounted pxd volumes\""
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `puppetbin` instead of `puppetbindir` and `puppetpath`",
      "reference": "currently the puppet-agent package doesn't symlink files into /opt/puppetlabs/bin. Also many puppet acceptance tests that execute on Unix assume puppetbindir is a single directory (windows doesn't have this issue). So I think if we want to unblock testing, this should just be changed to `h['puppetbindir'] = '/opt/puppetlabs/puppet/bin`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "any point in keeping this here ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think we need this check. Instead `Entries.merge` should check that its argument is correctly sorted (in addition to the existing pre/post check on the method receiver)."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is not really good to mix different code bases. @TheMarex I understand the point about placing code into cpp file, but we still need to move templated version into an impl header, remove references to offline code here and keep template instantiations in a cpp file to avoid rebuild. So offline code could instantiate own implementations using private impl headers. Otherwise we again make wrong dependencies into OSRM code and block changes in separate projects."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Then, where is it removed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The tests are not run concurrently? (I don't know. Better check.)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Regardless of scale?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `--telemetry` option.",
      "reference": "Nit: should not we hide them from printing out?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is the reason to modify those things? I noticed it breaks the examples using `asyncio`"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "WHOOOOOOOPS! so this is a wire protocol breaking change. I deployed a dev version of yarpc 1.9 to demo-yarpc-go and it caused bad request errors because it couldn't determine the procedure anymore. (in coordination with yarpc-prober)"
    },
    {
      "prediction": "I don't think it's a `Set` here, but it's a `Set` here.",
      "reference": "if we keep this, can we stick to our convention of using UPPER_CASE for constants? Otherwise this looks like a floating variable to me."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "You probably don't want to assume that `self.underlayer` has a `seq` attribute."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This apparently breaks the language selection."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do, but I'm not sure why this is the right thing to do, but I'm not sure why this is the right thing to do.",
      "reference": "since we're not using mysql, do we need this migration?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i'm not sure about htis naming here. both the word partition and adjustment are very ambiguous and it's not clear what it does. i would maybe go for something less generic and more concrete like `GOV_CLOUD_SUPPORT`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "unfinishedFlows might not be the same as activeFlows. Will it cause confusion here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same, remove the error handling."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `MvvmCross.Core.ViewModels` interface.",
      "reference": "We should not change this at this time."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "We may also update the docstring in the AnchorGenerator's arguments at around line 15."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "FormatHandle isn't current typesafe w.r.t. requiring *VULKAN* handles... so this slipped through."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "What kind of dependency is here, I think we have own implementation of event wo external dependencies"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Throw an exception instead"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "we shouldn't need the `FactoryBot.` in these. Ok to leave for now since all of these specs have them. Can clean up later"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Isn't the better option to actually do `$this->getDisk()->url($uploadsPath)` without changing the filesystems config? Not sure why you think that change is required but it's definitely not getting merged."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Not sure if we need this. It's not tested because it only guards against a new conditional definition of a dunder method in a built-in package. I am fine with leaving it out."
    },
    {
      "prediction": "I think this file should be included in the project root directory.",
      "reference": "Is this the only task in this library? If so this is good, if not then we should do it for each task."
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "I am not sure what is 120 and what is 10. Hence unable to review."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Not needed anymore"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `pingpong` package.",
      "reference": "Please not abbreviations"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This shouldn't get stomped over on line 207"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "are they not 1-indexed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I know that previously this check was here but @ralph-pichler replaced it with the `CheckTimestamp` field stating that checking against `Timestamp` was incorrect. @ralph-pichler can you elaborate?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`short_version = __version__`"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Required for the SparkDataFile SerDe"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Do you want to make this an assertion instead?"
    },
    {
      "prediction": "I think this is a bug in the GNU General Public License (GNU General Public License).",
      "reference": "When updating the copyright, we tend to cover previous years, not just the current. So, if we started the file in 2015, we'd update to say 2015-2016. I'm not sure if there's a legal requirement surrounding this, but it's the convention we and many others have adopted for code."
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "Wait, so it looks like this function is called _every_ time we fetch the root node, i.e. we do an MD head fetch every time we fetch the root node? Not for this PR, but it seems like we should make that unnecessary, since this function only ever does anything when head is `nil`, i.e. the first time. Maybe add a TODO?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Why are you changing this?"
    },
    {
      "prediction": "I don't know how to handle multiple services?",
      "reference": "`json.RawMessage` is a `[]byte`, which is already a pointer. Why do we need to have pointer here if we just reading this value?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "should we actually switch to `All` or just add `0.4.0` explicitly to the list of supported CNI versions? What is a new CNI version is released?"
    },
    {
      "prediction": "I don't think this is a bug in the source code.",
      "reference": "pylint might complain that this isn't alphasorted?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "It seems that NetworkService is behind a feature flag because it's still experimental. If we see new issues, we should look at flipping this back off."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think it makes more sense to have this be a method on TaskStatus. Also, nit, Backend, not BackEnd."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could you please elaborate on why you need all this magic here? In which cases do you want the same id to be returned? Does this work the same way for all backends?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: `PluginConfigs` feels a little better"
    },
    {
      "prediction": "I think this is a bug in the probe.go.",
      "reference": "think we need to find out the root-cause and fix, instead of just removing `NoError`? it erred b/c `context canceled`, so call this before context cancelled is the right fix"
    },
    {
      "prediction": "I think this should be a `Put` method.",
      "reference": "Please expand \"later behavior\". Presumably something to do with the prefetch logic?"
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "The `response` variable is not used, it can be removed, also the fmt.Errorf."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string.",
      "reference": "Do you find this really easier to read?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "A small nit: This variable should start with a lower case letter."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Where is this used for Node?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Is `<your-id>` really easier to understand than `<your-identity>` for CLI user? For me, `identity` seems like a concept we use publicly, and `id` is just an internal shortcut for it."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "nit.. `if` .. `else` for logging probably can be avoided.. maybe only log that an internal group was created for cluster group"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "There's a lot of changed tests -- but no new tests. You need unit and integration tests for this."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "WithMessage what gas limit is?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why are these skipped?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We'd better add the `json:\"metaServer,omitempty\"` here"
    },
    {
      "prediction": "I don't think this is the right thing to do with `pip install --no-deps` and `pip install --no-deps` and `pip install --no-deps`",
      "reference": "So... when we want to install mitmproxy with pinned dependencies, we first install all pinned dependencies, and then in a second step install mitmproxy as editable, making sure that no additional dependencies are sneaking in.  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "not sure how this got in master, but the linter is unhappy about it so I fixed it here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "No need for this TODO anymore, right?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "I would assign the key you're looking for into a variable first, and then use it in the comparisons."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the plugin manager.",
      "reference": "Would be better to normalize it at the start of the method to pass through to all the other calls"
    },
    {
      "prediction": "I think this is a hack, but it's a hack, but it's a hack.",
      "reference": "This can't exist here either because the code editor can be used on other models than CMS templates. You could probably implement this as a `hint` property (so `hint: cms::lang.cms_object.safe_mode_enabled`) on the codeeditor formwidget instead though and I'd be fine with that."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This line is unnecessary."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "How did this compile in the first place? Is there a matching declaration in a header that should be removed too?"
    },
    {
      "prediction": "I think this is a bug in the MRuby code.",
      "reference": "Please remove the colon at the end, and merge the PR once the CI succeeds. Thank you for the PR."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `go-bindata`?",
      "reference": "whoops. this should be protoc-gen-doc, since that is the only bit left that is built out-of-tree (everything else is either downloaded or built via modules already depended on by spire's go.mod)"
    },
    {
      "prediction": "I don't think this is the case for the `AzkabanEventReporter` class.",
      "reference": "The convention is to use <p> see the google style guide and use checkstyle to check. You can change it later."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Using non-keyword args after the keyword arg (parent-self) will cause a SyntaxError."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think you'll want to add some YARD docs to this method to get the PR approved  "
    },
    {
      "prediction": "I don't think this is the case where the `out_variant` is set to %NULL.",
      "reference": "Hmm, AFAICT `*out_variant` isn't explicitly set to `NULL` in the `ENOENT` case."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: \"Failed to configure TLS for SDK client\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "please update your branch to the latest `master`. This change was already made in #4359"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This line should be formatted"
    },
    {
      "prediction": "This is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "\"default 65536\" Not sure if it's important to state, but block_processor_full_size has a different default for fast_bootstrap."
    },
    {
      "prediction": "I don't think this is the default value for GasLimit.",
      "reference": "remove unnecessary whitespace changes"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are these conditions covered elsewhere ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "the above check (by transitivity) checked for `in_data.name_id == out_data.name_id && in_data.name_id != EMPTY_NAME_ID && out_data.name_id != EMPTY_NAME_ID`. The final check of `out_data.name_id != EMPTY_NAME_ID` is missing now."
    },
    {
      "prediction": "I don't think this is a problem with the `event_handle` parameter.",
      "reference": "The event handle is being passed by reference, so the dereference on 591 is actually correct. To follow the convention that variables be declared before executable statements, please change the code to the following: struct _fpga_event_handle *_eh; fpga_result result = FPGA_OK; int err = 0; if (!event_handle) { return FPGA_INVALID_PARAM; } _eh = (struct _fpga_event_handle *) *event_handle;"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "reorder includes to be alphabetically ordered"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Rename `need_unmap` to `unmap`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `chaosctl`?",
      "reference": "In line 28, it has been declared twice, so removing `cm` should not impact, can you explain me little bit? :)"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "i don't think these unexported functions belong on the public interface, they can exist solely on the struct."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I'm not entirely clear on why this is necessary?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `save_session` method.",
      "reference": "Why do we need to cast to `str` here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The ignore import above should be unused now and can be removed."
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "redundant null check?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "initialization of available ram is here"
    },
    {
      "prediction": "I think this is a special case for RTL.",
      "reference": "Can have negative numbers with the '-' on the right (`10-`) by just using line 610."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Shouldn't we use store a message which indicates that there was no available checker command? By the way how is it possible that metadata.json doesn't contain the checker command? Maybe this was the case in the earlier versions?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Given that this is a boolean predicate, maybe it should be `full_backtrace?`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the license.",
      "reference": "Just curious why the blank line here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I like the idea, but we don't want a dependency on mitmproxy in pathod."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why not adding this to the interface and keep passing the interface (as the interface is internal I don't get why you're not adding it there)"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "`PY310` should probably be imported from `pylint.const`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Can we propagate this error up the stack?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why reference is converted to table?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You shouldn't use assert for runtime errors."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `input[form]` polyfill.",
      "reference": "Does this really belong in the vendor directory if you wrote it? At very least, should it get its own repo somewhere in addition to being dropped here?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I think it would be better to place the rule name before the message. Messages are of varying lengths and the rule names will end up misaligned"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Can we remove the argument from this message? A message will include a line number already that points to the place in the code that has the problem. I think we can remove it."
    },
    {
      "prediction": "I don't think this should be used.",
      "reference": "This whole class is now a mix of virtual and non-virtual. I tried to see what would happen if I made everything non-virtual in dev, and the build still passes. It turns out that none of the other methods actually need to be virtual. Can you make *all* the logging methods either virtual or not for consistency? Thanks."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This looks a bit cryptic to me, and also it contains a dash. How about `mymysterium.url`?"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "You did notice the no newline at the end of this file, right?"
    },
    {
      "prediction": "I don't think this is the case for the `CodeFlow` object.",
      "reference": "Here's the object model change. `CodeFlows` is a set of objects of type `CodeFlow`, rather than a list of list of `AnnotatedCodeLocation`. Exactly parallel with `Stacks`."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Sorry, one more thing... You should use `app.config` instead of importing it directly. See the code below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was correct before; \"setup\" is a noun and \"set up\" is the verb form."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "What's the reason for this change here? I didn't see it mentioned in the PR and it's a bit of a confusing param name  "
    },
    {
      "prediction": "I don't think this should be a function, but it's not a function, but it's not a function.",
      "reference": "I wonder why ~ and not a wildcard instead?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "when will this happened? if happened, just ignore it Silently?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "3x the smaller size would be around 17k, and we need it to be at least about 13k, which is 2x the larger size. I'd probably set this to 15k to split the difference and hopefully avoid needing to update this again as tests change. This is minor, though."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "@scottpurdy, strictly speaking, should this scenario raise a ValueError exception instead of AssertionError?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Can you please add open source disclaimer?"
    },
    {
      "prediction": "I think this is a bug in the wirepb package.",
      "reference": "I dont want to do composite keys on purpose to verify at compile time if the message is completely filled out appropriately @sectioneight"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "don't need this line, since it is not tested in api_test?"
    },
    {
      "prediction": "I think this should be a better way to check if the CStorVolumeReplica CRD is found.",
      "reference": "Does this mean the list operation is done for all the namespaces? How to list the volume replicas per namespace?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I suggest adding `class_agnostic` as an argument of `batched_nms()`, with the default value False."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's a string, but it's not a string.",
      "reference": "@rdblue, did we not add the name on purpose?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why is this now public?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I guess we should backport some deprecation for this?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `path_for` method.",
      "reference": "Moving this code inside the last case statement doesn't seem right. Why are we defining `name` and `is_relative` variables there if we aren't using them anywhere?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I would say just change REGARG: no need for a separate thing."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "we can remove this template, it is no longer in use"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `array_key` and `array_key2` and `array_key2`.",
      "reference": "This doesn't look like it has as much coverage of the recursive code as it once did."
    },
    {
      "prediction": "I don't think this is the default value for the security groups.",
      "reference": "Do we actually expect users to provide more information here than possibly a SecurityGroup ID? If not, then this should probably use a new type, otherwise users might be confused by what options would be respected/ignored when used in this context."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This seems like a new dependency on rometools. Do we need it?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Waiting for the pull takes a long time. This message informs the user that at least one of the images being pulled is available. Please leave."
    },
    {
      "prediction": "I don't think this is a bug in spire.js, but it's a bug in spire.js, but it's a bug in spire.js.",
      "reference": "I can not think in a good use for it, but may we allow a way to setup a fake with a hook for logs? this fake is special, and we may need access to some of thoe logs, at the same time it may be an overkill because we dont want to test \"sql\" implementation but results.. but we can create some tests with end to end logs in some scenaries, What do you think about it?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I don't think you should be changing the dag unilaterally at parse time. If cores isn't specified, then it isn't specified."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Instead of just \"See SubscriberOptions....\", say something like \"Use ... to choose between the two.\""
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Use with statement for `f`"
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "It's a small style point, but could you remove the \"extra\" space before the colon that precedes the return type? This would make it more closely match the prevailing style in these tests and in the standard libraries."
    },
    {
      "prediction": "I don't think this is a good idea to do with the `ResolveBranch` method.",
      "reference": "seems clunky to me to have an `MDOps` interface method that some implementations don't implement. Perhaps define a separate interface, like, `BranchResolver`, and then callers that have an `MDOps` object can check via type assertion?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This change should also probably go into the corresponding method of the abstract By class?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "File is not `gofmt`-ed with `-s` (from `gofmt`)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This is likely to return an error value if the client fails to read the response we write, which is why I chose to ignore this error."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `is_upfront_shutdown_script_enabled` option.",
      "reference": "this method is not used"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `self.url()` and `self.zoom.reapply()`.",
      "reference": "Right now it's a bit unclear that this needs to be called explicitly by the implementing class. If, for example, there's another backend, it won't get this update unless we add the same function as webkit. Could you either add a note to this docstring explaining that this needs to be called, or find some way to automatically trigger this so the webkit override isn't needed (and some override passed on webengine)."
    },
    {
      "prediction": "I'm not sure why this should be done here, but I'm not sure why this is the right thing to do.",
      "reference": "Why this change (test name still says \"must pass with metadata\")?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Another nitpick: parens around the arg pretty please"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This spec can be modified, giving you extra strength (Check this fetch key doesn't work and therefore returns `nil`)"
    },
    {
      "prediction": "I don't think it's a string, but I'm not sure if it's a string, but it's not a string.",
      "reference": "Oh, I guess I mentioned/pressed this point in the other issue, that this should probably go into the httpserver package. In fact, so should the const above this (URLPathCtxKey). These are specific to the HTTP server."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Not added by you, but we don't really need the '5' here.."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "The vendor prefix is still being used on Chromium based browsers like Edge Chromium and Chrome. Did you mean to remove this?"
    },
    {
      "prediction": "I don't think it's a string, but it's not a string.",
      "reference": "I don't think this is needed anymore?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is the only occurrence I see in the code where we now need to convert from a boolean protobuf wrapper to a boolean pointer. This felt a little cumbersome here; should we consider moving it somewhere else as a helper function?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Need you to delete the `version_` from `HostInfo` struct ?"
    },
    {
      "prediction": "I don't think this is the case, but it would be better to use `node.getAttribute('xml:lang')` instead of `node.getAttribute('xml:lang')`.",
      "reference": "This could be the cleanest looking check we've got. Great job Jey."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Who invited yoda?   In all seriousness though, wouldn't an `if (empty())` be better here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `appRouter.showDirect('/');` and `appRouter.showDirect('/');` and `appRouter.showDirect('/');` and `appRouter.showDirect('/');` and `appRouter.showDirect('/');` and `appRouter.showDirect('/');` and `appRouter.showDirect('/');` and `appRouter.showDirect('/');`",
      "reference": "You can use `appRouter.goHome` to do this (It's defined in site.js), it's less hacky than overriding the href."
    },
    {
      "prediction": "Should we remove this part?",
      "reference": "When could this happen?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I assume this was removed because it was redundant? and conflicted with the now dynamic contentType? Edit: Oh I see it being set was moved to the `PostSegmentAsync` call."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Here is a newline missing"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Did you mean to make this http rather than https?"
    },
    {
      "prediction": "I think this is a bug in NVDA.",
      "reference": "The updated copyright header should be: # Copyright (C) 2006-2018 NV Access Limited, yourname"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure if this is the case.",
      "reference": "wow :+1: , i do not even know how this test works."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with MvvmCross.Plugins.Visibility.Platform.Uap.",
      "reference": "File should be renamed `PlugIn` -> `Plugin`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I scanned the new test cases quickly. Do we have one for an egressIPPool with multiple different IP ranges?"
    },
    {
      "prediction": "I don't think this is the default behavior.",
      "reference": "you can use a different name, like `maybe_activate` or `is_active` without `component` in the method name as this is used in the class name. E.g: `$component->should_component_be_active` is using twice the `component` word"
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "I think this might not be a complete enough check: what if `options` is `null`/`undefined`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `admin_users_path` and `admin_users_path` are the same as `admin_users_path` but `admin_users_path` is the same as `admin_users_path` but `admin_users_path` is the same as `admin_users_path` but `admin_users_path` is the same as `admin_users_path`",
      "reference": "Useless assignment to variable - `user`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `tar -xf ${archive_name(release)} -C ${TRAVIS_HOME}/erlang.tar.bz2`?",
      "reference": "I think we would want to keep `-O` instead. I wonder how this worked before, though.  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "another alternate option which doesn't have the risk of too many entries (when user keeps providing keys in different order) Have the dictionary as before If tagKeys lookup fail, sort and lookup again. If fails, insert both original tagKeys and its sorted one to the dictionary. So that we only store atmost 2 entries per key set. And we only do a single lookup in hotpath, as opposed to 2 look ups."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to call `updateWrittenBy` and `updateWrittenBy` and `updateWrittenBy` and `updateWrittenBy` in `updateWrittenBy` in `updateWrittenBy` and `updateWrittenBy` in `updateWrittenBy` and `updateWrittenBy` in `updateWrittenBy` and `updateWrittenBy` in `updateWrittenBy` and `updateWrittenBy` in `updateWrittenBy`",
      "reference": "if (out != nullptr)"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "In the listenstore you catch the exception and then pass it on via Raise. However, here you do not catch the exception. You should catch the exception, but since this is a minor aspect of this page, perhaps show an error message when the count cannot be loaded in time. Then the rest of the page can still be rendered, rather than failing the whole page."
    },
    {
      "prediction": "This is a hack.",
      "reference": "wouldn't it be simpler to just add `or transfer` here? That way the more complicated set of conditionals down below don't have to get more clauses."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "ditto; please fix everywhere"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can you break this line into two parts - the first line makes the option help text for `--sftp-server` and its too long! `Specifies the path or command to run a sftp server on the remote host. The subsystem option is ignored when sftp_server is defined.`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I reverted that one in a previous PR because of a CI failure but it was actually unrelated"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "The for loop is useless here, since any error will make the function return."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Fix file endings here and elsewhere."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I'd better increase `buf` length to MAXPATHLEN and not cut p->get_project_name() output twice"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Please remove the prints, even though this code will be trashed."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Not sure if you added deliberately but I've seen these popping up; is goimports adding them?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think we might need some special handling for `Spec.ControlPlaneLoadBalancer.SecurityGroups`, it looks like we are currently only handling the case that `Spec.ControlPlaneLoadBalancer` is nil."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `norm_cfg` or `norm_eval`?",
      "reference": "Is this from a third-party library?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be the case if the tabindex was removed.",
      "reference": "Please put the `el.tabIndex > -1` in the first part of the expression. The matcher will run on every node on the page, so we should put the fastest part first."
    },
    {
      "prediction": "I don't think this is a bug in mysterium.",
      "reference": "`identity` is unused now, is it for future usage?"
    },
    {
      "prediction": "The `unwrap` function should be used instead of the `unwrap` function.",
      "reference": "This would have assisted me a lot! I am on the \"functions\" page more than any other page in the docs"
    },
    {
      "prediction": "I'm not sure if this is the main module, but it's not the main module.",
      "reference": "I think it's better we keep `(` and encode with default encoding (utf-8)."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "this is gonna be different in an IDE vs from gradlew??"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Do we not already have something for isolating syntax?"
    },
    {
      "prediction": "This file is not part of Invenio.",
      "reference": "1: D100 Docstring missing 4: I102 copyright year is outdated, expected 2014 but got 2012 158: D103 Docstring missing 168: D101 Docstring missing 170: D102 Docstring missing 180: D102 Docstring missing 187: D102 Docstring missing"
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "how **to** deny"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "The only beef I have with this is that it's app domain global."
    },
    {
      "prediction": "I think this is a bug in OpenBSD.",
      "reference": "Can you link to the GitHub issue and/or PR so that it is easy for future readers to find out more about this?"
    },
    {
      "prediction": "I don't think this is the case for the `priority` field, but it's not the case for the `priority` field in the `priority` field of the `pAllocateInfo` field.",
      "reference": "Typical to report the value found as well as the valid bounds."
    },
    {
      "prediction": "This is a hack.",
      "reference": "maybe we want 0 as a default value?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "can we get height from sf at very beginning of the function and use that as height of the block?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Does this have to be public and in the primary namespace?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm a bit confused. Doesn't `mdWriterLock` already synchronizes calls to this function?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `getProviderReference()` method.",
      "reference": "Does it make sense to generate a dailyMotion url without the video reference? It does not to me, but can we throw an exception here?"
    },
    {
      "prediction": "I don't think this is a bug in GoogleCloudPlatform.",
      "reference": "Why the separation of imports here?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `ast.ParseSource(src)` and `ast.ParseSource(src)` and `ast.ParseSource(src)` and `ast.ParseSource(src)` and `ast.ParseSource(src)` are the same as `ast.ParseSource(src)` and `ast.ParseSource(src)` and `ast.ParseSource(src)` and `ast.ParseSource(src)` and `ast",
      "reference": "Random extra newline."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "No need for this variable."
    },
    {
      "prediction": "I'm not sure why this is a good idea.",
      "reference": "Why not use `msg` directly below?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `@SuppressWarnings({\"checkstyle:IllegalType\", \"checkstyle:VisibilityModifier\"})",
      "reference": "I think other places changed to use `Deque` instead of suppressing the warning."
    },
    {
      "prediction": "I don't think this is the right thing to do with it.",
      "reference": "missing: utility, cstddef also: vector is already included in the header (interface requires vectors as in/out types)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `babel-transform`?",
      "reference": "I'm not sure this is necessary in the config here, as Jest would be setting the global `fetchMock = ''`. See below."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Can `mFolder == null` happen during regular operations? Or is it only so we can be lazy in tests?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I'd suggest using the actual MIME types here - so `text/plain` and `multipart/alternative` or does that cause problems with what postgres allows for enumeration names? If so then maybe just replace the slash with an underscore?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the team name.",
      "reference": "Ohh. `TeamName` is actually a \"friendly\" name displayed in the Catalog - not the name used in the CLI. So I guess we'll need a new variable here. (That is, this is going to be mainly a `quilt.yaml` change. You won't need the `.lower()`, though.)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Nit: Don't move it between `require_dummy_response` definition and usage, this can live above or below :)"
    },
    {
      "prediction": "I think this is a hack, but I think it's not a good idea to do this, but it's not a good idea.",
      "reference": "With the current code, it not work if `EnableCatchupFromArchiveServers` is disabled. to fix it: in getDNSAddrs, change the predicate to `if wn.config.EnableCatchupFromArchiveServers || wn.config. EnableCatchupFromArchiveServers {` and in the catchup/service.go and catchup/catchpointService.go, use the `PeersPhonebookArchivers` only when `wn.config.EnableCatchupFromArchiveServers` is enabled."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why not make `SearchForNodes` do a `GetOrCreate` for the root node? (Not advocating for it, but just wondering if there's another reason than avoiding having to pass in the path.)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": ":+1: amazing that this has been missing since it was originally implemented"
    },
    {
      "prediction": "I think this is a bug in OrcFileAppender<D>",
      "reference": "Just want to note here that although we do check `length` while writing to choose whether to close and start a new file, that doesn't happen for ORC already so it is fine to use a FS call in this method."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "nit: I feel multiple `if (...) { return ... }` is more readable than `if ... else ...`."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "This is needed for us to work in IDE UTs"
    },
    {
      "prediction": "I'm not sure if you want to use the `--show-trashed-files` option.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I don't think this is the right thing to do with this function.",
      "reference": "this `label=` is docker specific, while here in libcontainer there shouldn't be any mention to docker. `DisableSecOpt` and `DupSecOpt` should just deal with `disable,role,type,level`. Both CRI-O and docker should just pass `disable,role,type.level` stuff and not `label=...`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You need to declare variable `recurse` above, same place as `localTime`."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Why does `clone` not already copy `xdensity` and `ydensity` from what it is cloning?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Curious - do we do the same for traces (when no ActivitySource / legacy source are added)? (and why we want to do it for metrics?)"
    },
    {
      "prediction": "I don't think this is the case for the first time.",
      "reference": "@aimanrosli23 For the changes in file SdMmcPciHci.c, please make sure that you do not revert the changes made by the below commits: SHA-1: 49accdedf956f175041040e677163b7cbb746283 * MdeModulePkg/SdMmcPciHcDxe: Hook SwitchClockFreq after SD clock start SHA-1: c67617f3c677c342efde780e229f841f4e0f6c7e * MdeModulePkg/SdMmcPciHcDxe: Add retries for sync commands SHA-1: 6d387610855ee27b49cb720de29ed809ea59dadc * MdeModulePkg/SdMmcPciHcDxe: Read response on command completion SHA-1: 63fd7f389874081ea37452b1f79ac013d52755e3 * MdeModulePkg/SdMmcPciHcDxe: Do not map memory for non DMA transfer"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "You'll also need to add `webelem.Group.all` everywhere as that matches as well"
    },
    {
      "prediction": "How to do this? I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I",
      "reference": "Does this need to be an ERB template?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "do we want to register this in the mock server for testing?"
    },
    {
      "prediction": "I think this is a bug in the test case.",
      "reference": "shouldnt this be `0:996` (+4) so the 1000s below fit?"
    },
    {
      "prediction": "I don't think this is a problem with the `__enter__` and `__exit__` and `__exit__(self, exc_type, exc_val, exc_tb)`",
      "reference": "The docstring of this context_manager should be updated. As now ``sort=False`` is valid, it should just say it disables sorting regardless of whether the NdMapping has ``sort=True`` or ``sort=False``. I also think the line 'Should only be used if values are guaranteed to be sorted before or after the operation is performed.' should just say something else - maybe just that the initial ordering (whatever it is) should be preserved?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This tests failed unless I swapped the order here. Perhaps some new class transform broke the old form?  "
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "extract the port and set to `debug_java_port`"
    },
    {
      "prediction": "I don't think it's a relative path, but it's not a relative path.",
      "reference": "When the argument list is `[\"one\", \"two three\"]` then you concatenate it as you do it here, you won't be able to get the original list back with split. You need to annotate the list items better. (Or if you won't do the split by yourself, the called shell will do it. So you need shell escaping. How portable is that?) The main driver to change this in `intercept-build` was to get rid of these concatenation and splitting errors. The current compilation database parser in Clang understands the `arguments` filed... So the question, why don't you pass the command around as a list instead of a string?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "`ctx` is unused in EnablePiped"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we have both a list of valid sessions and an instance variable if a session is destroyed?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "nit : I think that it would be \"cleaner\" to set the `flushcount` to nil in case of an error nice catch ;-)"
    },
    {
      "prediction": "I'm not sure if this is a test, but it's not a test.",
      "reference": "You may want to use assertNull"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Break out tests for events into their own tests rather than placing them in other ones. That makes it easier for us to figure out where problems lie and to do a TDD-driven implementation over new APIs."
    },
    {
      "prediction": "I don't think this is the right thing to do with the wlr_output structure.",
      "reference": "Why did you remove this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why we need another error printouts? We already have it inside addMapping.."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This LGTM, but I'm curious if this fixed a specific error you were hitting?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Actually we rely on this functionality in cgroup v2, where the subsystem is empty."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "suggestion: use `core` package name"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `get_option(\"compute.max_rows\")` instead of `get_option(\"compute.max_rows\")`.",
      "reference": "I think we can entirely remove this `limit` parameter for now to be consistent with other APIs."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit: `Resource Groups Tagging API` -> `Resource Groups API`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This type of list + delete always make me a bit uneasy but guess there's no atomic way to do this...... Could you put a todo to retry the \"ClearRepository + delete repo\" flow a few times? Basically, imagine a new image is added right after we call `ListImages`, then `DeleteImages` will not delete that newly added image. Then the delete repo call will fail"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You can remove this since ES6 modules are strict by default. And thanks for contributing to the Jellyfin Project."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Why did eip1559 go from a list (0xf9020280.....) to a wrapped string (0xb902060ff9020280...) and not just concatenation (0x0ff9020280...)? implementation detail or is this how it sits on the wire now?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@wallyqs Since on Windows it would be `\\` instead of `/` I just look at the suffix past `configs/`. Let me know if that's ok or not."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "nit: Remove this assignment because it is not necessary."
    },
    {
      "prediction": "I think this is a bug in glnx_openat_rdonly.",
      "reference": "This seems like a common enough pattern to offer an equivalent wrapper in `ot-fs-util.c`, no?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Wouldn't this crash the app if the user is currently listening to a stream?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This looks like an unrelated change? What is it for?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Wait, what is this doing? Is this a way to create methods that are only accessible from tests?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Is it more reasonable to return some errors here, such as returning error codes (403 and so on?) ?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `dom.nextSibling` and `dom.nextSibling`",
      "reference": "Thinking out loud... would `_nextDom` be a better name for this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Turns out the unittests also had a false positive."
    },
    {
      "prediction": "I think this should be an abstract class.",
      "reference": "I think these method names would be clearer if written as \"Create a {type} counter|gauge|measure with given name\". eg \"Create a int64 counter with given name\" \"Create a double gauge with given name\""
    },
    {
      "prediction": "I don't think this is a bug in the Lua script.",
      "reference": "it pushes a boolean, so it has to be explicitly casted to boolean with != nullptr, same with all other similar stuff"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It would be nice to have an equivalent of this call on `DataWriterImpl::enable`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Isn't this PENDING?"
    },
    {
      "prediction": "I don't think it's a `form` tag?",
      "reference": "minor detail, why aim to sanitize title if tile is empty (in some cases)? worth adding an && to check for that."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Code shared by ParentChildrenSyncDownTarget and ParentChildrenSyncUpTarget moved to ParentChildrenSyncTargetHelper"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "The bug is not about the priority , But we use 2 config items CAPACITY and SEQUENTIAL to control 1 action: thoughput. If 'sequential' is given to 'False' as default in configfile and then I use 'capacity' to 10 in my test.yml , the 'capacity' 's priority should be higher than default 'sequential'. So, I suggest we use only one 'capacity', it is enough. '1' is sequential, more than 1 is capacity, None is sys.maxsize."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "I don't know if I'd call any of these FAST tests integration tests. They are unit tests for FAST. They use a mock plugin which doesn't actually start any external processes, etc."
    },
    {
      "prediction": "I don't think this is a valid version, but it's not a valid version.",
      "reference": "Can you provide corresponding UT for this."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "nit: this should be below the yarpc group"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "singleCaseSwitch: should rewrite switch statement to if statement (from `gocritic`)"
    },
    {
      "prediction": "I think this is a bug in Typha, but it's a bug in Typha, but it's a bug in Typha, but it's a bug in Typha.",
      "reference": "Please log once here at Error level \"Failed to connect to Typha, will retry...\""
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Do we need the forXDP parameter in runBpfUnitTest? If not, I think better to revert in order to save a few changes."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "So we fix it only for kinto and not for all cliquet resources?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "No empty line between"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "We have `ResolveRootfs` in `libcontainer/utils` so maybe use that one here?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Just curious, do we have positive test covered somewhere?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Style error, put a space between `if` and `(`"
    },
    {
      "prediction": "I don't think this is necessary.",
      "reference": "It's a bit odd to have a \"disable<x>\" boolean, though it looks like you already do that for a few other flags."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Why did you pick two hours for this?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "What about \"enter new password\"? That would be a bit more consistent to the `ReadPasswordTwice` usage in cmd_init."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Another redundant import"
    },
    {
      "prediction": "I think this should be a better way to do this?",
      "reference": "What kind of errors might cause us to reach this point? Could any of them be recoverable i.e. might work if we asked the same server again? Similar question for below, but perhaps with a slightly different answer"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is the difference between GraphType and graph_type. Naming should be more accurate."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "hmmm in docblock of contructor it is EntityManagerInterface....maybe it should be that way.... :confused:"
    },
    {
      "prediction": "I don't think this is the case for the default chemical feature.",
      "reference": "I'm curious why you went the route of adding a new method name for this. Given that you it would be possible to just have an an overload of `GetPos()`, and that this change breaks existing code, I wonder why you chose to go this way."
    },
    {
      "prediction": "I'm not sure if this is a `stripe.Subscription` or `stripe.Subscription` is a `stripe.Subscription` or `stripe.Subscription` or `stripe.Subscription` is a `stripe.Subscription` or `stripe.Subscription` or `stripe.Subscription`",
      "reference": "Does this need to change `'active'` to `'Active'` and that? Or is that done in CSS or something?"
    },
    {
      "prediction": "I don't think this is the default value for maxFrameSize.",
      "reference": "Why are these constants public? They should also be listed above members."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "This TODO isn't related to this change. We should remove it."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "`FieldMetrics` is parameterized, but this is a bare reference. Could you update it? I think it should be `FieldMetrics<?>` since the metrics are not necessarily for the written value type, `D`."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "@cijothomas do we want this to be `Set` or `Add`?"
    },
    {
      "prediction": "I think this is the default value.",
      "reference": "Why are we dropping GasCap?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we end the text with a .?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could this instead keep the `go_native` and add to it \"or the last exit was the special reset exit\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Oh, I missed this one: The other instances of `this` you've added as lambda contexts aren't really needed, although they're harmless. However, in the above connection, the missing context is `panel`, not `this`. Please correct it! Clazy may show warnings about lambda contexts (I don't use Clazy) but, if so, that's a problem in clazy: it isn't smart enough to know about them."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "can we add a try / except around this to make it more stable? I like the idea of any mistakenly un-quit drivers closing down after the process is quit (the java server does this... also i forget to do driver.quit often when i use the command line repl :) )"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "when would this happen? backward compatibility?"
    },
    {
      "prediction": "I'm not sure if this is a HTMLElement",
      "reference": "I'm not sure what the value of this is. So far we've solved this by always doing `tagName.toUpperCase()` for everything. I think we should stick with this."
    },
    {
      "prediction": "I don't think why this is a bug in mayactl snapshot list command?",
      "reference": "This command displays available snapshots on a volume."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `EmitOptions` option.",
      "reference": "`spb` is the standard package name we use for this proto."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "/javascript/firefox-driver is the Selenium implementation of a WebDriver for Firefox. Since it generally isn't W3C compatible, it shouldn't change. We can just drop this change."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "is this pr support parallelly process application?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Based on the assumption that when `EnablePulls` is `true`, `CanEnablePulls` must be `true` as well, then this `if` check is redundant. Actually... we have `AllowsPulls` now... why not use that?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I am not sure why the API requires both project name and project ID as inputs. Wouldn't it introduce more opportunities for clients to make mistakes?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I believe this was happening for several different flash messages - should we add `now` to all flash messages? (there might be a downside to doing that, but I am not sure what it would be)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the exception listener.",
      "reference": "There is no docblock on the parent method. Also, not related, but I forgot to typehint the `$templating` constructor argument above."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Silly me. This shouldn't be done in the tests, but instead in the actual definition of ValidPHPVersions on arm64. Same with Mysql and MariaDB."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't this work as well for Disjoint?"
    },
    {
      "prediction": "I think this is a bug in acmeapi.Error.",
      "reference": "You've not updated the `o.Status.Reason = fmt.Sprintf(\"Failed to retrieve Order resource: %v\", err)` line below here when you changed this, so here we are checking `errUpdate` but will print the contents of `err` instead."
    },
    {
      "prediction": "I don't think this is a problem with the `SocketPoller` module.",
      "reference": "Doesn't this need to include `Errno::ECONNRESET` to fix the issue?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Please consider keeping the config key in one line as it will help in case someone is looking at how this config is used. public static final String PROJECT_CACHE_THROTTLE_PERCENTAGE = \"azkaban.project_cache_throttle_percentage\";"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This is a hard one, naming-wise... `ListPowerSelectorEntries` is logical given `ListSelectorEntries`. Another option could be `ListMatchingEntries` or even `FindMatchingEntries`. :shrug:"
    },
    {
      "prediction": "I don't know how to handle this, but I don't know how to handle it.",
      "reference": "This should be called `Uint` or `Uint32` or simply using our `Uint64` type instead. All of our numbers have varint encoding. It's not inherently a varint."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `edit` and `pygment`?",
      "reference": "No need for this when you don't need to customize anything about the argument."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We're now going to have 3 `#sections_accordion` will need to see how JS behaves. We should probably switch to a class selector instead"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "did you mean to leave this in here?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Mention that it only applies to Windows. This is kind of implied, but better to be explicit."
    },
    {
      "prediction": "I don't think this should be used.",
      "reference": "again: it is a bad practice to have some global parameters with such common names for unit test purpose."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Should we use `\\DateTimeInterface` or `DateTimeInterface` and declaration of `DateTimeInterface` in `use`?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "What do you think of moving this stack related constant to the `stack` pkg?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Hm, I guess that you're doing this here since `WellFormed` is on a `transactions.Transaction` and not a `transactions.SignedTxn`, but quickly grepping through our code, it looks like we always a `SignedTxn` around when calling `WellFormed` (except maybe some tests?)... this doesn't have to happen here, but maybe we should update that in a separate PR since this really feels like a `WellFormed` check."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This story also needs the default padding."
    },
    {
      "prediction": "I think this should be an exception, but it's not a problem.",
      "reference": "Hmm why did we remove the randomness about which (confusingly) different exception to throw here? This randomness was (is?) useful to help test that Lucene indeed catches `FNFE` and `NSFE` interchangeably."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Hm, so before in that case `current_collection_id` looks like it was actually an uninitialized pointer. It seems weird to me that the tests pass both ways. I haven't looked closely at the tests - is there something wrong there that causes this to spuriously pass before?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "s it the best way to tag \"foo\" of \"`define foo ...\" with constant kind? Introducing \"d/definition\" kind and tagging the \"foo\" with the definition kind is an alternative way. Using the unified kind \"constant\" in many areas reduces the information that client tools get from a tags file. In my experience, it is better to tag different things with different kinds. If ctags hides the differences, and just reports various language objects as \"constant,\" in some cases, a client tool must parse the raw .sv source file for distinguishing whether a given tag is \"`define\"'ed or not. IMHO, ctags should not be too smart. Instead, ctags should be stupid; it should report what it sees in source input files as-is to client tools that will do something smart."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "is this a breaking change? If I'm not mistaken, this is translating a user-provided `wtimeout` in the connection string into `wTimeoutMS`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we rename this file to `lambda_echo.py`, to be more descriptive and in line with the other files in this directory? (all files in this folder are lambda functions, after all)"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "why not do it like this ? <pre><code> const ( Kill Action = iota Errno Trap Allow Trace ) <pre><code>"
    },
    {
      "prediction": "I don't think this is the right thing to do with this.appenders[i].CloseAppenders(expireTime)",
      "reference": "lock(this) is a bad practise, since you lock the entire instance. cosider: var appenderCache = xxxx. lock(appenderCache) { Thread.Sleep(TimeSpan.FromHours(5)); } while inside AppenderCache instance lock(this) { is blocked 5 hours. } Its always better to make a class private lock objects."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we use the constant above?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "I think something like `size_res` would be more descriptive."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `report` and `error` and `metrics_message`?",
      "reference": "Oh lol so this was...really more of a bug?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Well, it is providing a platform neutral way of calling Task or TaskEx. We could just call it PlatformTask."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Typo: this should free `xwayland` instead"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is it ok to use \"math/rand\" instead of \"crypto/rand\" here? Do we need to protect this ID somehow?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why did we have `logxi` in the first place? Maybe it makes sense to remove it from `glide.lock? It will safe us in the future from using logger which is not working."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is there a reason to use `getUNF()` and `UNF` in the same block?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Again this seems odd that megacheck cares"
    },
    {
      "prediction": "I don't think this is the right thing to do with this.",
      "reference": "I assume this will resolve to nil if this isn't in the config?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I looks like we can make `allowOptionalMappings` non-optional since we have another overload without it. (I thought this generated a compiler warning, but maybe it's just R#)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "` per scale.` -> ` per scale.` need to clean the unnecessary blank space"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "there's no import for Export"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i don't think we want/need to make the node API available over UDS"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "How about to skip if and returning null and return a result of `ArticleFacade::findById` directly?"
    },
    {
      "prediction": "I'm not sure if `Array.prototype.map.apply(this,arguments)` is called.",
      "reference": "I think this change is currently unnecessary. I like the idea of `map()`, `filter()`, etc. returning vanilla JavaScript arrays rather than mongoose arrays, but I think that's a bit too heavy of a change for a patch release. I think that all we need for this release is the `if (!parent || parent.$__.populated == null) return;` change."
    },
    {
      "prediction": "I'm not sure if `git rev-parse HEAD 2>/dev/null` is present, but `git rev-parse HEAD 2>/dev/null` is present.",
      "reference": "how about \"unknown\" instead of \"fafafaf\"?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "nit: do we gain anything from naming the output error `err` in this definition?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This can happen with any dialog. Maybe the best place to add this change would be the dialog component instead."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should this be `TearDown` since it now calls this method? Something I would like to see is, on test failure don't teardown completely instead leave the FAST repo in place with the stderr and stdout files and direct the user to that location. What do you think?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "There's not particular reason to use a short name. Can we use a more descriptive name for the metric? Perhaps \"negativeLogLikelihood\"?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "not handling in case of `repr` makes the behavior probably a little too unpredictable. Is there a reason not to, apart missing stuff in the `repr`? Does it lead to some problem?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Remove the finally?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Build on AArch64 fails because WCHAR is not defined."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Do we use this const?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think this may need to be `SetCertificateRequestAnnotations` as it returns a `CertificateRequestModifier`  "
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "it would likely be better to do this in the Identifier.by_scheme_name method itself."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "@janette looking at this test code, I'm pretty sure that it's going to give a false positive. Where is it actually checking the contents of the first four datasets against expected values? All the assertion at the end of the test seems to check is that at least four datasets exist."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `es6.spec.symbols` instead of `es6.spec.symbols`.",
      "reference": "Would this break things if Ghost is run in a subdirectory or no?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `new_value` and `new_association_value`?",
      "reference": "maybe switch the order in order to make this a positive assertion instead of a negative one? i.e. `if key =~ /id/` first."
    },
    {
      "prediction": "I don't think this is a bug?",
      "reference": "Is this an oversight for some code in the body?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Reason for adding this? I couldn't find where you are retrieving it back."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `h2o_mruby_eval_expr(mrb, \"require \\\"preloads.rb\\\"\");",
      "reference": "Can we expect adequate information emitted to the log in case either requiring preloads.rb or doing the requires in preloads.rb fails? If the answer is yes, I think we can merge this PR right away."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "How about a `app/views/layouts/pages.html.erb` layout that contains the HTML head, body, wrappers and yield's the `new-topics` template into it? I think we might be able to delete the `app/controllers/pages_controller.rb` file at that point."
    },
    {
      "prediction": "I'm not sure if `path` is `_id` or `_id`?",
      "reference": "This is a coarse solution. This check is helpful, but you should also add a check in `$__version()` to avoid calling `isSelected()` if `key === false`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Passing only needed data to make it can be reused by `planpreview` package where there is no deployment data."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we rename those to `CustomClientAuthentication` (same for Router) to remove ambiguity between Authentication and Authorization (permissions)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is the name \"IMvxFormsViewPresenter\" too close to \"IMvxFormsPagePresenter\"? Perhaps something like \"IMvxFormsNativeViewPresenter\" or \"IMvxFormsPlatformViewPresenter\" or inline with Forms naming \"IMvxFormsOnPlatformViewPresenter\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`typeof child != 'boolean'` maybe?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why && changed to || ?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "nit: not a big deal right now but spec assigns ID 0 to InitAddress"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "/javascript/firefox-driver is the Selenium implementation of a WebDriver for Firefox. Since it generally isn't W3C compatible, it shouldn't change. We can just drop this change."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `setZoomFactor` method.",
      "reference": "There are various places where `setZoomFactor` is used but `fuzzyval` isn't set: - `__init__` and `on_config_changed` (should be okay as `init_neighborlist` gets called which essentially does the same) - `zoom` (calls `zoom_perc` with `fuzzyval=False`), which is used by `:zoom-in` and `:zoom-out`. Are you sure this won't break those calls? (Yes, I know there should be tests for this - I'm working on that.) Other existing places probably should get simplified."
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is a testing node, so we don't sort it.",
      "reference": "Is there a benefit to keeping this in RefinementSettings? Or could we move it into its own class in TestUtil?"
    },
    {
      "prediction": "It is not possible to call Err().",
      "reference": "I would have expected the Ready method to need to change to be a `<-chan Result` instead of a `<-chan map[string]Result`. The difference being that now the Ready channel can produce more than one set of results. In fact the name Ready is inaccurate now since its not about the query being ready but just a mechanism to deliver results. If this should be a follow up PR that is fine, lets create an issue for it."
    },
    {
      "prediction": "This is a hack.",
      "reference": "why? what if we want to access those methods outside of azkaban-common?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure how to do this?",
      "reference": "Rename file too"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Need to populate the `RequestID` field for these errors. This can be obtained from r.RequestID i think, but need to make sure. The `r.RequestID` should of been populated from the `UnmarshalMeta` handler list."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is the `final` being removed here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the MIT Licence.",
      "reference": "Maybe let's take this opportunity to change easylogging to a git submodule?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we just be generous and elide all extra whitespace? `strings.TrimSpace`"
    },
    {
      "prediction": "I'm not sure if this is a tablet, but I'm not sure if this is a tablet.",
      "reference": "This is an inaccurate API that has outlived it's purpose. We can't make the determination of phone (vs) tablet, with a 7\" screen in the mix. Also, with the advent of fragments, this API means very little now. It's not being used anywhere, since we switched to `ActionBar`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This change means that users can't easily see which version of the selenium server they're using. This is `info` level information."
    },
    {
      "prediction": "I'm not sure why this is a mock.patch here, but I'm not sure why this is a mock.patch here, but I'm not sure why this is a mock.patch here.",
      "reference": "You should just use `with patch(...):`, so it unpatches it automatically. Also, much simpler."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `MvxMainThreadDispatcher.Instance`?",
      "reference": "This didn't use to work for me. Are you sure that returns the correct instance from startup?"
    },
    {
      "prediction": "I'm not sure why this is a method call. I'm not sure if this is a method call. I'm not sure if this is a method call. I'm not sure if this is a method call. I'm not sure if this is a method call. I'm not sure if this is a method call. I'm not sure if this is a method call. I'm not sure if this is a method call. I'm not sure if this is a method call.",
      "reference": "Looks good. Eventually we could remove some of these constructors, but for now adding these two seems the way to go"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@jalavik should be have somewhere enum/list/registry of possible tags?"
    },
    {
      "prediction": "I don't think why this is a problem?",
      "reference": "why is this pylint disable needed?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `forseti-security` and `policy-library-sync-enabled` and `policy-library-sync-enabled`?",
      "reference": "The new sync feature is only being supported from within Terraform. Installations using the deprecated method will have this feature disabled."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This type of return (f'xxx') is not recommended, it is recommended to return 'xxx'"
    },
    {
      "prediction": "I don't think this is the case where we don't have a ZMM register, but it's not the case where we don't have a ZMM register.",
      "reference": "I would make this level 1 or 2."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `vmware_fusion` environment variable, so we can't use `ENV['VAGRANT_VMWARE_CLONE_DIRECTORY']`.",
      "reference": "Is that path in a variable anyway? Not a big fan of hard coding it here."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `spiffeid/v1beta1` package.",
      "reference": "nit: Move `IdentityTemplateLabel` to be under `IdentityTemplate` to match the struct in config_crd.go"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Not necessarily related to this PR, but don't you think having a centralized place for all interactions with analytics might make this into a very big class? Is that something that you don't worry about until it happens?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "it seems that my terminal is dead when I press ctrl+c during running daisy cli today, is this PR fixing that?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If we are going to add config to specify the maximum message pool size, we should probably also add a parameter for the maximum nonce gap and pass it into the `IngestionValidator`. This could be done in this PR or added as an issue."
    },
    {
      "prediction": "I'm not sure if this is needed?",
      "reference": "please inline imports"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should IptablesPostWriteCheckIntervalSecs be set back to its previous smaller value, if use of the iptables lock is disabled?"
    },
    {
      "prediction": "I think this is a bug in Joplin.",
      "reference": "Please use packageInfo here instead. As it is used in `app.js`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "this seems unrelated to the rest of the PR, although related to the original report"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Would a check for added columns with non-null default be sufficient for aligned format?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this PR implementing compute service account for OVF import as well? I thought it's only image/one-step import? Btw, OVF importer uses \"-\" instead of \"_\" in flags (should be `compute-service-account`)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why change to element ?? in whole application use plural convention ??"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Tiniest nit but this can be `tabindex={-1}`, `width={11}`, `height={11}`"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use itk.Image[itk.RGBPixel[itk.UC],2] and itk.Image[itk.RGBPixel[itk.UC],2]",
      "reference": "Unrelated to this PR, we should remove this exception. We now require `numpy`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is the loop over vars and adding them to the subworkflow below in this file needed, since it's already done by NewSubWorkflowFromFile?"
    },
    {
      "prediction": "I don't think this is a good idea to use `starts_on.to_s(:simple)` instead of `ends_on.to_s(:simple)` and `starts_on.to_s(:simple)` instead of `starts_on.to_s(:simple)`",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Having to write this util makes me think that maybe we should have kept the csv_input stuff. I don't know."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Passing in and saving a reference to the `BlockCache` at init time is going to break if something calls `config.ResetCaches()`, because it replaces the `BlockCache` instance completely. This happens on user logout or by a manual write to `.kbfs_reset_caches`. So you probably want to give it the whole `config`, or maybe just the `config.BlockCache` function pointer."
    },
    {
      "prediction": "I think this is not a problem.",
      "reference": "I am not sure this could happen. st should be nil if the error happens. If it does happen, we could also do st.Reset(), since it is an erroureous state so it closes both sides of the stream."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'm guessing this was just added for debugging? Should probably remove it so we aren't modifying 3rd party libs."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This seems reversed... if `success?` is true, wouldn't we use `success`?"
    },
    {
      "prediction": "I'm not sure why this is a bug in Datadog, but I'm not sure why this is a bug in Datadog.",
      "reference": "This seemed like the easiest way to allow log level checks, it will require an update to the vendors tool, to ignore that file on update."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Should we disallow entry authors to unsubscribe to their entries?"
    },
    {
      "prediction": "I think this is a bug in the GNU General Public License.",
      "reference": "2016 should be 2017."
    },
    {
      "prediction": "I'm not sure if this is the case for development, but it's not the case for development.",
      "reference": "boolean exists = (existSchema != null) && (existSchema .getSummary() != null);"
    },
    {
      "prediction": "I don't think this is a good idea to use `cobra.Command.Run` instead of `cobra.Command.Run` instead of `cobra.Command.Run` instead of `cobra.Command.Run` instead of `cobra.Command.Run` instead of `cobra.Command.Run`",
      "reference": "It does not look idiomatic."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Generally, we do not use newlines between project imports, we only separate them from the stdlib imports"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "can this long line be wrapped?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `comparison-with-callable` method, but this is not the right thing to do with the `comparison-with-callable` method.",
      "reference": "I'd use the same message that I suggested in the release changelog."
    },
    {
      "prediction": "I'm not sure if this is a MongooseDocumentArray.",
      "reference": "Keep semi-colons at end of function defs please"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the parent.",
      "reference": "A little skeptical of `explain` being here. Why is this now a property of all commands?"
    },
    {
      "prediction": "This file is not used in the project root.",
      "reference": "License copied two times!!"
    },
    {
      "prediction": "I don't think this should be a class, but it's not a class.",
      "reference": "... their **superclass**"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'm not sure if this is the right thing to be doing here. It seems like there should be a more systemic fix instead of this patch."
    },
    {
      "prediction": "The `screenWidgetContext` property is deprecated.",
      "reference": "Not sure why these are up here   can we move these down to be part of the `@return` tag instead? This is what we usually do   (e.g. `getCurrentEntityURL`)"
    },
    {
      "prediction": "I don't think this is a problem with the `to_semantic_values` method.",
      "reference": "Layout/EmptyLinesAroundBlockBody: Extra empty line detected at block body beginning."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We keep who wrote the code anonymous."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Mention something in logs, that fake registration was used e.g. `Fake identity registered`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `setSettings` method.",
      "reference": "I think it would make sense to also set `internalWebPropertyID` to `''` here. Otherwise, it might keep its previous value (let's say a property was selected before, but then the user chooses \"Create new property\"), but since it always should depend on `propertyID`, that would be incorrect."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It might be reasonable to add a check that sanitization still fails here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not use attemptNo instead of another call to getAttempt? Even better, consider using a private method to calculate this string. This logic is in two places."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Yuck. Rails bug."
    },
    {
      "prediction": "I'm not sure if this is a subclass of the packet, but it's not a subclass of the packet.",
      "reference": "It's useally a common practice to not use `l` as a variable (we have disabled this test in scapy because our code has tons, but it would have PEP8 failed otherwise), but it would be better not to create any. In general, single letter variables are not liked that much. Especially with windows where the fonts make 1=l How about `lay` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "DRY these 5 lines into a function call, no?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "should we be trying to close here? or just return directly @fabxc ? same goes for `stopc`..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "just re-ordered for clarity"
    },
    {
      "prediction": "I think this is a bug in M_API server.",
      "reference": "Can you fix this also to print what is the IP address used to connect. Rename --> \"M_API server\" to maya apiservice"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This fails on Go 1.11 because `indexByte` is already defined in strings_go111.go. I would suggest simply renaming one of the two, for example you could rename the other one to `strings_indexByte` (that will be one of the things we'll drop when we drop Go 1.11 support so it's better to make that one look ugly instead of the function that we will likely keep for a longer time)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Now `dbType=' MockDbType.int32 '` is correctly interpreted and the value is rendered as an integer instead of a string; hence no more double quotes."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "typo in `$contend`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Nit: empty line"
    },
    {
      "prediction": "I don't think this is a bug in KBFSOpsStandard.",
      "reference": "I figured this was more fool-proof than trying to plumb the error up from everywhere."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We know debug and trace as globals exist and are defaulted to 0. In this instance we need to know that c is non- nil, srv is non-nil and logging is non-nil before we can trust this statement not to panic."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Good removal here for two reasons: we're redeclaring `app.ConfigPath` immediately below without having used the initial value, and `app.GetConfigPath()` will build the value using the same process as in this line anyway."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should BuildBase be removed?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "this was a bad Goland auto-import that I missed in the previous PR. Thanks to @rkowalick and @acruikshank for catching it"
    },
    {
      "prediction": "I don't think this is a bug in RWMol.",
      "reference": "Good catch here. Reading the code, it actually seems kind of dumb that `replaceAtom` needs to copy the atom it's passed. Ah well, we're more or less stuck with that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What's the reason for adding the output pointer here? I'd expect it to be derivable from the actual handler that's called."
    },
    {
      "prediction": "I'm not sure why this is a problem with the `annualized_savings` and `discounted_annual_payment`?",
      "reference": "I don't see tests for this (or the similar method on `Team`)."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `typeMap` property.",
      "reference": "should use Number instead of Long"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We had the checks for those two errors for a reason, why do we not need them anymore?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Why didn't you just switch to `range` here too?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `opts.TokenSource` option.",
      "reference": "I don't even think `nil` should be allowed, since it uses global state to get the client."
    },
    {
      "prediction": "I don't think this is a bug in the browser.",
      "reference": "You somehow got a change from `master` into your branch again, in e6d2167085688264e5ee6a81cfd2a7a8f10ded13. While it's not something terribly bad (as it will be fine after merging), it's kind of confusing, and I have no idea how it happens :laughing: Are you trying to update changes from `master` while working on your branch somehow? How do you do that?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Minor, can we drop the leading `!` and just swap the if and the else blocks?"
    },
    {
      "prediction": "I don't think this is the case where the number of proposal is not 0. I don't think the number of proposal is not 0. I don't think the number of proposal is not 0. I don't think the number of proposal is not 0. I don't think the number of proposal is not 0.",
      "reference": "`bbox_feats.shape[0] > 0` requires the number of proposal is not 0."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Just FYI, I had to remove this unused import because Travis/`npm run lint` were complaining."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the namespace LAMMPS_NS.",
      "reference": "format.h is not a system header but bundled with LAMMPS. This should be `#include \"fmt/format.h\"`"
    },
    {
      "prediction": "I think this should be a better way to do this, but it would be better to do it with the `visitDocValuesWithCardinality` and `visitDocValuesNoCardinality` and `visitDocValuesWithCardinality` and `visitDocValuesNoCardinality` and `visitDocValuesWithCardinality` and `visitDocValuesWithCardinality` and `visitDocValuesNoCardinality` and `visitDocValuesWithCardinality` and `visitDocValuesWithCardinality` methods.",
      "reference": "could we always call visitDocValuesWithCardinality? It seems to include the version check already?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "I think if they _don't_ specify a port, we should assume grid default (which is 4444)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This looks to be a breaking change. I know it will affect some of my code that uses the Tautomer enumerator."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Perhaps remove this line"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Ah, missed this one. Sorry: you don't need to test the atomic number here. that's taken care of above on line 683."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "roundInfo() is called by couple of places in consensus for safety, better test/verify the delay of return err due to this Sleep() would not affect the normal functionality, like consensus can still be reached, full-node can correctly sync"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "This 32 could go away too."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `notification::dismissed::${ id }` and `notification::dismissed::${ id }` and `notification::dismissed::${ id }` and `notification::dismissed::${ id }` and `notification::dismissed::${ id }` and `notification::dismissed::${ id }` and `notification::dismissed::${ id }`",
      "reference": "These props should be less specifically named since the component is generic, for example `anchorLink`, `anchorLinkLabel`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "In the future, it'd be great if we can separate commits or PRs that aren't in the same scope"
    },
    {
      "prediction": "I don't think this is the case for the `__gestures` attribute.",
      "reference": "can you define the string format on a different line, so it can be named, and so that it does not have to be constructed twice?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can we write a unit test for this."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Same as above, use `.delete('_autosave')`, not the command handler."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It isn't necessary to check whether there are projected ID columns. The code is shorter if the values are available by default, even if they aren't used. This fixes the problem where there are constants to add (like `_file`) but no identity partition values are projected."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Update after command rename"
    },
    {
      "prediction": "I don't think this is a bug in the source forge.pmd.lang.java.ast.ASTAnyTypeDeclaration.",
      "reference": "@KroArtem This is the Checkstyle violation. This import should be grouped with other `net.sourceforge.pmd` imports below, in alphabetical order"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `fs` package.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "This change seems unrelated to copying email addresses to the clipboard. Please limit the scope of pull requests as much as possible."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm assuming that there isn't a way for us to skip sending an fd here (-1?), and that we're allocating this fd just to send a legal but useless value across?"
    },
    {
      "prediction": "I think this is a bug in yarpcconfig.TransportConfig.",
      "reference": "might be good for the units (bytes?) to be in the variable name."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Metrics/BlockLength: Block has too many lines. [166/25]"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I'd end the sentence after `special indicator (line 3)`. And then start a new sentence: `The special field can indicate that the field specifies a reset, is a sequence ID, or is a timestamp for the record.`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with a list of bboxes.",
      "reference": "These empty lines can be kept."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "For some reason these tests started failing due to an extra `NEWLINE` returned from `h.query()`. Have not tried to check whether this may be a problem for real templates or not, just fixed the failing tests. Anyone with an opinion here?"
    },
    {
      "prediction": "I think this is the default propagation.",
      "reference": "It is better to have a method than a var."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "concurrent poller won't be larger than concurrent execution. Jump from 2 -> 16 seems aggressive. I suggest to use 8. Ideally, this should be dynamic config. :)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "List is redundant."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Please use a string resource here rather than the hardcoded string \"user\". This allows the app to be multilingual."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "@aswathkk Why did we remove this import? I guess we are using it."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why? I thought this is for graceful shutdown."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Can `result.stdout` or `result.stderr` be nil?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@mprobst Looks like the `isStdLib` function has been removed in the latest Python plugin. Any thoughts on how to handle this? The new version doesn't seem to have any relevant alternatives."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "How can there be a configured max ipset size? Surely we need to write ipsets with however many members are implied by the Calico datastore?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This code is passing a non localized string when it should be passing in a localized string or it should use the name of the item being deleted."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with this, but I'm not sure why this is the right thing to do.",
      "reference": "why not be consistent with `isNull` and `notNull` and return null?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Did we forget to remove this field?"
    },
    {
      "prediction": "I don't think this is the right thing to do with this.values().stream().mapToInt(elem -> elem.elementCount()).sum();",
      "reference": "What if there is no element?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I think you need to be careful to honour isTest and stamp here."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "why zero value for `arrayType` for the default value of the optional args?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@robinbonnes ~~Would you mind putting the array key and value on a new line - it makes it more readable as an array.~~ Never mind, see discussion below."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I've never seen us do this anywhere else - why here? Why not `address, meshAddress string`?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think it's necessary only for the earlier \"dynamic\" approach. I suppose it's not necessary in the eager one."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure if this is the case.",
      "reference": "Same here than [there](#r26168925)"
    },
    {
      "prediction": "I don't think it's a valid ID?",
      "reference": "Again we should think about moving this pattern to a static final field"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "haven't been implemented the `__constructor` for `NormalizerConfigPass` ?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Docstring is missing."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I don't see the reason of this return as it will stop loading in half because an error, thats bad imo. Or you load it all and report errors or you load nothing and terminate, the first is as it always was so I wouldn't change that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "change from AddPeer to AddPeers added a space in some occurrences"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Can you please revert changes to files in the `thoughtworks` package? This is legacy code and we will eventually phase out RC."
    },
    {
      "prediction": "I don't think this is the right thing to do with iptables.New(true, false)",
      "reference": "Do you remove \"s\" from \"iptables\" to IPTable\" on purpose? I feel it should be \"IPTablesRules\"."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: not your problem - but I wonder if this should have been a \"ConstantResponseRpc\" - which takes a name and a value .... maybe a more reusable concept."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "These changes have been resolved upstream. We can revert changes to this file when synced."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The description predates this diff but I think we can come up with something more grounded."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Let the Kind, APIVersion & Metadata follow the rules followed by Volume. What is the reason for a change for snapshot struct ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "seems that we did not strong depend servo no need to keep it? change to another one?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like this used to be UB before with an empty blocks and then calling `.second` on the `.front()`. Did it ever crash though?  "
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Sorry about the code churn here, reworking this use normal loops and async await made debugging far more straight forward. For example, if configuring the fail point fails you find out when stepping over that line vs having to look for the ultimate catch clause that handled it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is wrong and should be reverted"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think you'll need to add an import for runtime, before you can merge this PR. (Presumably it was already there for something else when you were working on this, but has since disappeared.)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Unrelated typo fix."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I don't think we need an empty value here; any middleware that wants a default value for empty placeholders will pass in what that value should be."
    },
    {
      "prediction": "The `--docker` option is deprecated.",
      "reference": "Why was this changed?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Compared to using traditional enums, I suggest to use `Status` or `StatusOr`, since they are more expressive and informative. Besides, isolating the definitions of error code of individual modules from the ones of the RPC interface is a good practice, isn't it?"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `invitation.email` and `current_user.email` and `invitation.email` parameters.",
      "reference": "Use the return of the conditional for variable assignment and comparison."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "just realised... This breaks things since there is not selenium types module, is there a PR for this?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "move to line 23 below"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "the first problem i found in the passcode change flow is that these two lines were happening in 'lock()' but not in 'showLockActivity' which is what the passcode change flow calls. I've just moved them to happen in that method."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Doing this adds the actual resources themselves to the dictionary. I think for now, there's no way to know what the resource config provided may be, as we don't permit resource config on `build_solid_context`, so this part can be omitted."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `resubscription.fulfill` method.",
      "reference": "1 trailing blank lines detected."
    },
    {
      "prediction": "I don't think this is a test.",
      "reference": "I would personally prefer a filename without an abbreviation, a newcomer to the project wouldn't be able to translate \"pv\" to \"partition-value\"."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This check looks odd to me. I can't quite grok it. Why is it needed now? What's changed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change is needed because otherwise the path was being changed from `path/store/jetstream` to `path/store/` and files stored differently after re-enabling."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "is this necessary? doesn't `client.close()` imply all sessions will be ended?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Extra line, it's not needed here."
    },
    {
      "prediction": "I think this is a hack, but I think it's a bug in rspec-puppet, but I think it's a bug in rspec-puppet, but I think it's a bug in rspec-puppet.",
      "reference": "Is this OK to add in the spec helper? I need to call `Bolt::PAL.load_puppet` so that I can use the new `Bolt::PAL::Issues` module when verifying that plans forbid functions."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "or is it `i < length - back.length()`? `\"12345\".padTo(10, 'a')` should be `12345aaaaa`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "custom_imports -> custom_hooks"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I don't get why are we baking new hash structures to represent phases, sections, questions. We are not only loosing the references defined in models but also we have to figure out keys and values for this newly structures."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It's somewhat confusing that the `preload` parameter shadows the instance variable; maybe rename the instance variable to `globalPreload` or `preloadDefault` or so to prevent future confusion?"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string.",
      "reference": "Are we setting these values anywhere?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This has to be in front of all other includes"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "These changes make sense to me. @ricrogz : you wrote (I think ) the original version of this as part of #2553 Do you see any reason to not make the change?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`window.self === window`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "maybe we should keep one test case for ErrFileNotExists and update only one file for ErrWorkspaceNotFound?"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "Please add `ConsigureAwait(false)` here and on `ShutdownAsync` below."
    },
    {
      "prediction": "I don't think it's a good idea, but it's not a good idea.",
      "reference": "Isn't this a false positive? Why are we reporting `unused-variable` on a `del` operation with a `undefined-variable`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is it correct that `SessionDto` should be here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "sorry I missed this earlier. We no longer use ovs-ofctl for flow programming AFAIK, why not add this support to ofnet / libOpenflow?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Make this consistent with the other definition please `'false'` vs `false`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this is a good way to do it. :+1:"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `go-homedir`?",
      "reference": "Why this is needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we define this directly in the function `NewConnTrackOvsAppCtl` instead of passing this as an argument?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "False positives are annoying..."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is the infrastructure layer an appropriate one? I don't think so tbh, more like an application, or even a domain one."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Why is this required to turn the static readonlies into jitted const? Is this a bug in the jitter?"
    },
    {
      "prediction": "I don't think why this is needed?",
      "reference": "feel free to make this a \"typed\" named tuple (overriding __new__) if you are feeling frisky"
    },
    {
      "prediction": "I don't think this is the default value for MAX_SAFE_INTEGER.",
      "reference": "Would use parenthesis to explicitly state the associations of operands ```js const MAX_SAFE_INTEGER = Number.MAX_SAFE_INTEGER || ((2 ** 53) - 1)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The bug was caused by this order change in the last refactoring."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is already imported as docker. You're safe to simply use `docker.utils.kwargs_from_env()` below."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "No need to add this fun. Using RunnableActionsBuilder#AddActions instead"
    },
    {
      "prediction": "I'm not sure if this is a side-effect, but it's not a side-effect.",
      "reference": "I don't think it's possible to do this for hooks  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "wait(1ms) when sec=0. wait(0ms) waits forever so that's why this is better."
    },
    {
      "prediction": "I think this is a bug in h2o_hostconf_t, but it's a bug in h2o_hostconf_t.",
      "reference": "Do we need `domain` and `so_reuseport` now that we open new sockets immediately after calling `add_listener`?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "The formatting seems different from the rest of the code"
    },
    {
      "prediction": "I don't think it's a valid zone?",
      "reference": "What about calling this package \"parameters\"? utils\\parameters are utils related to parameters."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "what is the actual difference here?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Parsing URLs is hard. Any fixes should avoid manually parsing the URL."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is a private api, it doesn't need to return anything so `@group_level -= 1 if @group_level > 0` is preferred."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": ".GetValueOr(0) ... but really, shouldn't m_value_strife also be optional?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Working around a possible limitation in the JSDoc plugin's typescript syntax checking. This means the same thing"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should be readonly"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I'm not going to stop accepting the PR, but I really hate these artifacts getting dropped in the Python code just to stop things like coverage checkers and linters from complaining."
    },
    {
      "prediction": "I think this file is not used. I don't see it.",
      "reference": "FYI modifying an existing file generally doesn't invalidate the copyright date. The date here is when the copy right _begins_, so moving it later is arguably misleading-it still applies. Not a big deal, just something I've seen a few times in passing."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "Because the default value of allowedOrigins is * (all origins), so it isn't necessary to set again at all."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Style: indentation should be 4 spaces (2 indents) from the start of `Preconditions`."
    },
    {
      "prediction": "I think this is the only way to do this?",
      "reference": "I don't know why I suggested a html attribute at first (my bad), or maybe you think it makes sense. Otherwise, what about a simple class ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Probably want something more generic here like 'DMPRoadmap' so that other installations aren't using UoE by default."
    },
    {
      "prediction": "I think this is a bug in NLog.Config.",
      "reference": "Must this not change to `MustBeRethrownImmediately`?"
    },
    {
      "prediction": "I don't think this is a bug in opsv1alpha1.Traceflow, but it's a bug in opsv1alpha1.Traceflow.",
      "reference": "Can it be pointer?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not related to this issue but this condition seems weak."
    },
    {
      "prediction": "I think this is the default value for this field, but it's not the default value for this field.",
      "reference": "I think this might be a little more readable in two lines as: <pre> $preferredMarcField = $this->mainConfig->Record->preferredMarcField ?? 'fullrecord'; $marc = trim($this->fields[$preferredMarcField] ?? $this->fields['fullrecord']); </pre>"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "does this still allow this file to be used with Python installations that don't have numpy?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "what about 0? Version probably can' start with 0, but v10 is theoretically possible."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `IsRootedPath(string path)` and `IsPathRootedPath(string path)` and `IsPathRootedPath(string path)` and `IsPathRootedPath(string path)` and `IsPathRootedPath(string path)` are the same as `IsRootedPath(string path)` and `IsPathRooted(string path)` and `IsPathRooted(string",
      "reference": "Usually we consider APIs that have filesystem interactions to be part of IFileHelper, this would allow us to inject a testable implementation easily. `Path.IsRootedPath` doesn't access the file system. It is string comparison I believe."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Do we need to use quote? Why not `status: Init`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Nice catch ! I don't think I would have caught that, did you search the whole code base for pre-existing functions ?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Remove this line."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This is no longer called in any of our unit tests, right?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think typically K8s APIs will use `int32` and not `uint32`. I think we should keep it consistent with the rule `Priority` above. I believe that the rationale for using `int32` in general is: * some programming languages don't have native support for unsigned integers * it's easier to catch sign errors with signed integers, depending on the programming language (it it's negative, it's clearly an error but if it's a very large number, it could be normal or it could be a negative number overflow)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "If you end up changing grant to an association, this may need to change to a reference to enforce the foreign_key `add_reference :plans, :grant`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This won't work because `notification` comes from an API response here. I think this would be the same as the change to `Alert` where it would get `SmallSunSVG`."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This is not checked below?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Will this ever return a \"Stack does not exist\" error? Should we handle it silently here rather than making higher level packages do error checking?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "minor: at this scale, one import per line reads better"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should remove the default templates as well."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why not `let`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "ns -> DNS My first reading was this is referring to System.nanoTime and thought hrm?"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `start_date` and `start_timestamp` as a parameter.",
      "reference": "is there a reason not to remove the param now? I think the serdes will still work?"
    },
    {
      "prediction": "I think this should be a test case.",
      "reference": "`places=2` seems to be very poor comparison. Do you have any thoughts why is it fail with more strict checks?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we make level debug? Also just FYI, with debug level, we can add more detailed logging for better debuggability without concerning overwhelming logging message"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I needed to add this import for Sphinx to inspect C++ runtime objects properly. This should be the only code change in this PR."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Changes in this file aren't related to the PR, are they? You took the opportunity to change the group deletion to using the subscriber too?"
    },
    {
      "prediction": "I don't think this is the case for `None` and `Counts` as `None` and `Counts` as `None` and `Counts` are `None` and `Counts` as `None` but `None` is `None` and `Counts` are `None` and `Counts` as `None`.",
      "reference": "I'd probably move this into `MetricsConfig` as a private method. Seems like we only use it there."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Not clear here what you mean with this list"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Curious, is there a way we can get around this without suppressing?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think we this field in session, it's a serial number for proposal but not unique index itself"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Can't have two benchmarks with `Baseline = true`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `config.web.client_id` and `config.web.client_secret`?",
      "reference": "Same here: Empty line before and no `Internal dependencies` docblock (mandatory anyway once #217 lands)."
    },
    {
      "prediction": "This is a hack.",
      "reference": "sorry, the default value for this field is no longer allowed?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why does this work? I'd've expected that an admin could create a file anywhere."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "falling back to `x64` seems like a really bad idea given that the VS templates default to x86 these days."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Bit surprised by this. I would have thought either you want to set it for both mpl and bokeh...or alternatively it was only ever meant for bokeh and was always wrong?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Check modname instead, but only if it's a ImportFrom."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "How about `write.metadata.previous-versions-max`? No need to refer to these as a log."
    },
    {
      "prediction": "I don't think you want to use `RSpec.configure` instead of `RSpec.filter_run_excluding appveyor_agents: true`",
      "reference": "We generally do this via tags in the Rakefile, not separate environment variables."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Update after command rename"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`if X not in Y:`"
    },
    {
      "prediction": "How to do this with the metastore.hiveConf.getVar(HiveConf.ConfVars.METASTOREURIS), so we don't need to use the metastore.hiveConf.getVar(HiveConf.ConfVars.METASTOREWAREHOUSE), so we can use the metastore.hiveConf.getVar(HiveConf.ConfVars.METASTOREWAREHOUSE));",
      "reference": "Do we know why the pool is exhausted? In the past, we had a few leaks in the Spark catalog code which led to this. It can be also a valid use case too if we simply need a larger pool."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Logging in Bolt still seems to be a little messy. I think this is more correct than what I had before, but made sure I wouldn't overwrite an existing level. And if console logging gets more options, both debug and verbose need to be fixed here."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "This could be simplified (if including <boost/algorithm/string/erase.hpp> is fine): `auto address_string = boost::algorithm::erase_first_copy (address.to_string (), \"::ffff:\");`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is wildly unhelpful to users --- they need to know when a proxy has been registered."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `attachment_content_type` option.",
      "reference": "Why do we need `do_not_validate_attachment_file_type` is we're doing it in the previous line?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Loading login page right away only for the regular use case."
    },
    {
      "prediction": "I don't think this should be the case.",
      "reference": "IIRC this flag disables re-rendering entirely (`s/recursively //`)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "Did you test this redirect? @thornbill mentioned it might need `web` at the front, but if this works fine I'd rather leave it this way."
    },
    {
      "prediction": "This is a hack.",
      "reference": "FYI, this returned `StringValues` which is a value type (aka can never be null)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Oh no, that's a bug."
    },
    {
      "prediction": "I think this is a bug in yarpc.",
      "reference": "Let's leave a note in CHANGES to replace this with an error metadata struct or interface, unless it would be less effort overall to take a run at it in this change."
    },
    {
      "prediction": "This is not supported for the `mapTo` property, but it is not supported for the `mapTo` property, but it is not supported for the `mapTo` property.",
      "reference": "The changelog entry does a better job of explaining how this is used than this description. In particular, this says that you need to set `mapTo` if the underlying name is different, but not that `mapTo` *is* the underlying name."
    },
    {
      "prediction": "I don't think this is a bug in the source code.",
      "reference": "These imports will probably need to be refactored so they aren't here. That applies for all of the database drivers. The reason for this is because we sometimes want a driver to be available and sometimes we don't. When we include this library in our cloud offering, the sqlite3 connector needs to be gone because it's a security vulnerability and there's no use case for it in a cloud environment. But for flux itself, I can see how sqlite3 would be really useful and so I like this change. But this import needs to only exist within the tests and within the `cmd/flux` package. It cannot be here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We can use `getQualifiedKeyName` here instead. I will update."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `x-apple-diskimage` and `x-apple-diskimage` and `x-apple-diskcopy`?",
      "reference": "Could you clarifty why some of those are removed?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "`ctx` is unused in ListDeploymentConfigTemplates"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `data-toggle` property.",
      "reference": "nice to see the usage of block for a more readable link name"
    },
    {
      "prediction": "I think this is a bug in MPI_File_read.",
      "reference": "Can these use `static_cast<unsigned long long>` instead? Other than that, it's fine."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This output is only present when `DEBUG=True`. Does it really bother so much?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think it should pass wallet transaction as well, otherwise there will be 2 wallet read transactions in 1 threads (next in scan_receivable)"
    },
    {
      "prediction": "I think this is the best way to do this, but it would be better to do it with the `mmffVdWParamsIAtom` and `mmffVdWParamsJAtom` and `mmffVdWParamsIAtom` and `mmffVdWParamsJAtom` and `mmffVdWParamsJAtom` and `mmffVdWParamsIAtom` and `mmffVdWParamsJAtom`.",
      "reference": "RDKit::Utils is now in the namespace for localeswitcer... We could change it to something else."
    },
    {
      "prediction": "I don't think we need to do this here, but I don't think we need to do it on the MultiIndex.",
      "reference": "@itholic, can we fix it in `_normalize_keyword_aggregation`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to use.",
      "reference": "It seems like we have the main plan in the database but the downgrade plan in the code. Probably okay for now, but as our thinking of how downgrades/plans develops we may want to consolidate."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "we shouldn't add a bunch of static initializers 'everywhere' in the code. Probably just one would be good, during the construction of the 'RemoteWebDriver' class."
    },
    {
      "prediction": "I don't think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "do we need both flags? maybe infer that `clef-signer-enabled` whenever `clef-signer-endpoint` is defined?"
    },
    {
      "prediction": "I'm not sure if this is a bug in the source code, but I'm not sure if this is a bug in the source code. I'm not sure if this is a bug in the source code. I'm not sure if this is a bug in the source code.",
      "reference": "Do we need this? I didn't see css files (only scss)."
    },
    {
      "prediction": "I don't think this is the right thing to do with remote_hosts.",
      "reference": "This feels like a weird `if not ... or not` to me. Can you talk out the intent here?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `annual_payment` and `discounted_annual_payment` and `discounted_annual_payment`.",
      "reference": "Align the parameters of a method call if they span more than one line."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `AbstractFacetPackage`?",
      "reference": "`@package *` can be removed as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@ScottGarman is there a reason that `redhat_fips` needs to be a beaker platform? Why can't it be another platform that beaker just understands as `redhat`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Where is the other place?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to use, but I'm not sure if this is the right thing to use. I'm not sure if this is the right thing to use.",
      "reference": "Are you subclassing from `UserList` instead of `list` to satisfy some constraint of Jython? My main concern here is that this is a subtle breaking change to the API because `UserList` is not a subclass of `list`. This has the unfortunate side effect of breaking any user that is using `isinstance` checks to see if a `ResultSet` is a `list`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `avatar_tiny_laurels` method, but I'm not sure if this is the right thing to do with the `avatar_tiny_laurels` method.",
      "reference": "We can DRY the above three functions"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Only no good is good code. Nice that you were able to remove all this duplicate stuff!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looking at the code, it seems very odd that this method even exists in the SurfaceNamer, since it is only implemented and used in the PhpSurfaceNamer, and in fact the RetrySettings class name is hardcoded elsewhere. WDYT of just removing this method from SurfaceNamer and PhpSurfaceNamer?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "these interfaces are defined twice. we should use only one and have it in `storage` package maybe"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is the wrong context for usage of `global` keyword. It need only be used inside functions."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this change should be described in the changelog. I'll update it when merging if nothing else arises."
    },
    {
      "prediction": "I think this should be a function that returns a dispatcher.",
      "reference": "Just to stay consistent with naming let's call it CreateGRPCDispatcherForOutbound. Also rename 'CreateDispatcherForOutbound' to 'CreateTChannelDispatcherForOutbound'"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This will always need to be displayed to users."
    },
    {
      "prediction": "I'm not sure why this is a good solution.",
      "reference": "This looks very much like `repr` now (we miss 127 though) - maybe just do `repr(x)` + strip outer parantheses?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "I don't see this field is set in task_generator.go. worth to double check if we put the timestamp when creating replication tasks."
    },
    {
      "prediction": "I don't think this is the case for `nextObject` and `nextObject`?",
      "reference": "nit: I prefer the space before and after this check to make it very easy to scan when reading through code"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "should users also do a triple-flush?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is the implication of removing these from the test? I thought the idea was to have all types supported by `docstore` here, and do things in the drivers to make them support them (e.g., list of size 2 for complex). If you're removing them because firestore doesn't have native support, then we're going to end up only testing the intersection of all types supported by all drivers; we need a better way."
    },
    {
      "prediction": "I'm not sure if it's a list, but I'm not sure if it's a list. I'm not sure if it's a list. I'm not sure if it's a list. I'm not sure if it's a list. I'm not sure if it's a list. I'm not sure if it's a list. I'm not sure if it's a list. I'm not sure if it's a list.",
      "reference": "Let's also adjust the somewhat weird type signature here as well. This probably should be `typing.Any` instead of `str` in the last line if we intend to support ints."
    },
    {
      "prediction": "I think this is a bug in the tests.",
      "reference": "The body can just be `os.RemoveAll(dir)`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this covered by regression tests? Also you might make a patch onto refactor branch."
    },
    {
      "prediction": "I'm not sure if this is a SolrPingResponse, but it's not a SolrPingResponse.",
      "reference": "This is maybe more of an admin request? WDYT?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Here I thought of `toHashMap` and later add `toTreeMap`. But I start to see, what you may have in mind. Alternatively we could provide a `toMap` and `toSortedMap`, which is great, too. On the other hand is always good to be as specific as possible. What do you think?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "maybe localProjectAppNames? Just a thought."
    },
    {
      "prediction": "This is a hack.",
      "reference": "This isn't new, but getHeightWidth is now defined in block_svg.js, block_render_svg_horizontal.js, and block_render_svg_vertical.js. One of these should be unnecessary."
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "I can't see any reason why this would fix a failure in `a.True(confirmed, \"txgroup\")`. We might have an issue elsewhere, but increasing the wait time wouldn't help."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `--collect-perf-data` option.",
      "reference": "This section needs to be modified; crontab format differs between OS releases (Debian and CentOS, at least)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "if we think this is likely to be augmented with a additional 'run coordination' features or configuration in the future, we could make it an object of some kind instead (or an enum, if we think there may be other resume modes in the future besides just on/off). Just imagining 6 months in the future, it would be unfortunate if there were 7 new args here as the feature gets more complex"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`affine_grid` and `grid_sample` are currently unused. We may remove it from `ops/__init__.py` to speedup the loading of mmdet."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is there a reason why you need to support negative `AttackTimeout`? Why not just throw an error?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with pandas.core.dtypes.common.infer_dtype_from_object",
      "reference": "nit: an unnecessary change?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the body.",
      "reference": "Is trailer parsing something we have to do in this PR? It would be really helpful to separate stuff like this into smaller, self-contained PRs."
    },
    {
      "prediction": "I'm not sure why this should be done here.",
      "reference": "Any chance of a wait-forever situation here? Is there a reasonable timeout?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "line is 165 characters"
    },
    {
      "prediction": "I think this is a hack to make sure we don't have to wait for the `RefreshNamespaceCache` to be called.",
      "reference": "is this for cross DC case?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Remove this line."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe it would make sense to use `webmVideoCodecs` here and just append `vpx`. I'm not sure if av1 is currently supported when transcoding to webm though. It looks like it can be included in the mp4 transcoding profile now."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it would be better to do it. I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "Interestingly, this has nothing to do with replication, no clue what this means here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is that because we don't provide a UI for these?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Standard is either to use `HappyPath` (CamelCase) or `happy path` (lowercase sentence). I usually prefer the latter."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "instead of using blkMemDao, we could generate a blockMemDao, and then use it as the second parameter."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit(2/10): `topology && topology.description != null`;"
    },
    {
      "prediction": "How to do this?",
      "reference": "why the space? I may not know all the style conventions."
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Should be \"should fail if the **dt element** has a parent <dl> with a changed role\""
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Just to be clear: 1. This is required for compression, right? 2. This won't actually result in our dynos serving the assets, since they'll be served via the CDN, correct?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `save` method.",
      "reference": "not sure about removing this ping @Soullivaneuh"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do, but I'm not sure why this is the right thing to do.",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "If instance could not be found when the provider id is set, `findInstance()` returns `ErrInstanceNotFoundByID` error. So that during reconcileNormal(), we don't create a new instance. In `reconcileDelete()`, when ErrInstanceNotFoundByID is seen, deletion continues to clean up even if the instance is gone (may be manually deleted)."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I would recommend making this a Tuple&lt;ReplicateValue, IColllection&lt;object>> You only need to convert things to strings if you need to persist them in Settings or something. If they only need to live for the life of dialog, you can keep everything as objects. You can use \"null\" for the ReplicateValue for when they have not chosen a property."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think there is no point providing action key here, as it will be called specifically, rather than randomly"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "`XUnitIntegration` doesn't need to cache this anymore."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we have something line `# noqa` there instead? I think it's fine like this though."
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "this variable is used in both branches so I've decided to declare it above"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`setFlags()` overwrites the previous flag, we should be using `addFlags()` to append flags."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Need `return` after this."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would say we should not use the `CacheableResponseTrait` within the `JsonResponseTrait`. Traits within traits tend to lead to a bad developer experience as it can be really hard to find the actual method you're seeing in the implementing class, and in this case it looks like we're using _both_ the cacheable and the JSON traits in the same controller, so it's redundant anyway. I'd recommend just removing that use statement from `JsonResponseTrait` and make sure `ChaceableResponseTrait` is included everywhere it's needed specifically."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "This change is unhelpful: it precludes users from knowing which ports are being used for what purpose within the system."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Whoa, we weren't doing this before?? Derp."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm surprised we didn't go with something like `flow := f.Flow.Copy()` to take care of all the fields at once, but as long as it works it's good enough for me"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We would like this code to run, even when `config.XDPEnabled` is false, so that Felix can clean up its own XDP state after a restart."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the ASTAnyTypeDeclaration.",
      "reference": "I'd declare this field `qualifiedName` private to hide it. Unless it really needs to be modified from somewhere else... (e.g. unit tests..), but then, we should find a solution, where this field can stay private."
    },
    {
      "prediction": "I don't think this is the default URL template, but it's not the default URL template.",
      "reference": "is this exhaustive? or rather, any psudo header started with `:` is un-parsable/invalid in HTTP/1 right?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Is this change implying something or just seems fit b/c regardless of outcome the sessions should still be length 1?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Maybe throw an exception if there is more than one, so that discovering the lack of support is easier when someone tries to use it down the road."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Prefer single-quoted strings when you don't need string interpolation or special symbols."
    },
    {
      "prediction": "I think this is a bug in Travis.",
      "reference": "I feel the name of this function could be better, conveying it's a predicate. Something like `HasDockerTestEnvironment` or `CanRunLocalServerTests`, etc."
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "This seems unrelated to your PR, how did this end up in here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is `username` expected to be case insensitive?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "File is not `gofmt`-ed with `-s` (from `gofmt`)"
    },
    {
      "prediction": "I'm not sure if this is a bug in netsourceforge.pmd.util.FileUtil, but I'm not sure if this is a bug in netsourceforge.pmd.util.datasource.DataSource.",
      "reference": "Is there any point to the deprecation? If someone was using these APIs, can they continue to do so in any meaningful fashion now that you've disconnected them from the PMD internals? Normally \"compiles but doesn't work\" is considered a bug.  "
    },
    {
      "prediction": "I'm not sure why this should be called.",
      "reference": "You can remove the `QItemSelection` import in this file now."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "Use `std::shared_lock` and `std::try_to_lock_t`. BTW. Why we fail on contention?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Not sure what this actually does, but do you need to add `\"\"` here? Or does `[\".jsx\", \".js\"]` work too?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "let's group imports in the order: std third party first party"
    },
    {
      "prediction": "I'm not sure if this is a test, but I'm not sure if this is a test.",
      "reference": "So the tests run only when the db exists? Else everything passes?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "`Remove` is unclear. It seems the point is to allow the `FifoByteSink` to delete the underlying file. There seems to be an implicit contract that consumers of this interface call `Remove` after `Close` without necessarily understanding what `Remove` does. I get that it's a little awkward to have `FifoByteSink` delete the file in `Close`. It would probably be best to just remove this from the interface, since `AddSink` is working with an actual `FifoByteSink`. I would rename it in `FifoByteSync` to `DeleteFile` or `Cleanup` or something that's makes it more clear what's being removed."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Mentioned elsewhere but repeating again: would be nice to have units (ideally `Size *Bytes`)."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `--no-resolve` and `--no-resolve`?",
      "reference": "I think a test in `spec/integration` might help keep this file a bit more manageable, especially since we're just checking file contents and errors. But basically the same idea!"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This spec can be modified, giving you extra strength (Check this fetch key doesn't work and therefore returns `nil`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So this means that we can remove a callback via instr_set_label_callback(). Maybe consider adding another API function for removal, and add a new assert here such that cb != NULL?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "why are we using an instance variable instead of accessing the visibility method?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Ok. Can we just disable this linter?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is `test_data` and all other instances are `testdata` - does this change affect any test files, or are there actually no directories called `test_data` in the repo? (I just checked, it seems like there aren't...)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Fixing `lint` warnings that have existed for a while."
    },
    {
      "prediction": "I don't think this is the default cstor pool.",
      "reference": "Better to rename this to CASDefaultCstorSparsePool."
    },
    {
      "prediction": "I'm not sure why this is a class, but I'm not sure why this is a class.",
      "reference": "Since we'e not 100% sure if `close` will be called more than once, should we set `client` to `null` or add an `AtomicBoolean closed` that will then handle the idempotency issue?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the same name, but it's not the right thing to do with the same name.",
      "reference": "And here - what happens if name id is invalid"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "__toString() is not a part of QueryInterface"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: Could you add an empty line between `import datetime` (built-in library block) and `import numpy as np` (third-party library block)?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please remove `HIP_UNSUPPORTED`"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Having boolean parameters to change function behavior is not a good practice because it violates the principle of functions being responsible for a single task, so the need for this indicates we need to split something out of here instead. We can introduce a function like `getCurrentDateRangeDayCount` or similar, which does this."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Is this not required?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "savedStates is for confirmed states, not needed in working set"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Why should we move it into `bootstrap.go` file?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "In the next major version, I plan on changing the em-unit breakpoints to be pixel values to keep everything consistent. Would be great to handle this with pixels as well, but still allow em-units to be defined with a string"
    },
    {
      "prediction": "This is a hack.",
      "reference": "I don't think this will actually align the indexes, if you have > 100 tabs, the tabs over 100 will be misaligned. In addition with less than 10 tabs, there will be a pointless space."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "hrm, unsigned headers now won't be included."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "what if `$value = ' ' `?"
    },
    {
      "prediction": "I think this is a bug in SparkWrite, but it's a bug in SparkWrite.",
      "reference": "What about using `!files.hasNext` instead? I'm not sure we want to assume that the iterable can be consumed multiple times. Plus there's no need to consume the entire iterable just to check whether it is empty."
    },
    {
      "prediction": "I'm not sure if this is the right thing, but I'm not sure if this is the right thing. I'm not sure if this is the right thing.",
      "reference": "I think we could add bool addArticle here defaulted to false like its done in item class so std::string Container::getName(bool addArticle /* = false*/) const { and pass that variable to getNameDescription call"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What if a library function on the outside still calls the old method? It is then no longer blocked properly. Have you tested the change?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "@i110 Do you have an idea on how we should propagate errors that occur in this block? The error condition happens when i) `h2o_buffer_reserve` fails to allocate space (happens in master as well), or ii) `fill_cb` returns an error (unique to this PR)."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure why this is a good idea.",
      "reference": "Does this mean the times will show up in emails as UTC?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "What's the motivation for having one of these be a cycle and the other be a fixed color?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "What will be an empty entry now?"
    },
    {
      "prediction": "I'm not sure if this is the right-to-left side of the handsontable.",
      "reference": "Can I ask you to add jsdoc tag that would mark the prop as `@private`?"
    },
    {
      "prediction": "I don't think it's a directory, but it's not a file.",
      "reference": "Do you need this? Don't think you use it?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`this.` seems unnecessary"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "nit: can be removed before merging..."
    },
    {
      "prediction": "I don't think this is a `<div id=\"${id}\"></div>`",
      "reference": "Maybe a single quote would be compatible with airbnb style."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is not the right approach. The `Distributor` maintains a model of the current state of the Grid. That model already contains the information about every active session. We don't need to modify `SessionMap` to expose it further."
    },
    {
      "prediction": "I think this is the end?",
      "reference": "@Marwes @wolffcm This is the file where I made a change the the expected output. Its a little bit weird, but I think that the final output makes sense for the most part."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I think we probably need a util.Warning() here."
    },
    {
      "prediction": "I don't think this is a good thing to do here.",
      "reference": "Let's make have a signature that's consistent with `PhysicalKey.from_path`. Users should also have access to PhysicalKey since that class is part of the API (e.g., `Package.resolve_hash`)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "What is this directive for?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'd rephrase it as `Simplify chained comparison between the operands`."
    },
    {
      "prediction": "I'm not sure why this is the case for the first domain?",
      "reference": "so in the performance data fixtures, there will be references for the second domain only?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is wildly unhelpful to users --- they need to know when a proxy has been registered."
    },
    {
      "prediction": "I think this is a bug in MitmProxy.",
      "reference": "If there is no authority header (i.e. someone intentionally deleted it), I would argue we probably don't want a Host header in the replay either. How about we only add it if it exists, and do nothing otherwise?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "is there any unit test that can be updated to verify this?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "exiting at this point is leaking memory, take a look at the valgrind output. the sbuffer must be destroyed."
    },
    {
      "prediction": "I think this is a bug in pytest.",
      "reference": "i think you want a different flag and help like `--ffmpeg` or something; and you need to mark any tests you want skipped"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "this needed to change? or it was just some formatting thing?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "What's the advantage of doing it this way over, say, changing the `.circleci/config.yaml` to have `TRACE` as the `root.log.level`?"
    },
    {
      "prediction": "I don't know how to do this with `project_number` and `dataset_id`.",
      "reference": "typo: if -> of"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It'll be interesting to see who or what this breaks..."
    },
    {
      "prediction": "I'm not sure if we're using a WebDriver-backed Selenium, but I'm not sure if we're using a WebDriver-backed Selenium, but I'm not sure if we're using a WebDriver-backed Selenium, but I'm not sure if we're using a WebDriver-backed Selenium.",
      "reference": "This change is incorrect: the current log level is correct."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There are few cases like this where default logger is used from CLI/db tools. I would copy `NewTestLogger` to `NewCLILogger` and use it everywhere in CLI. In future these two might be different."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "While it provides re-use, this method does not make sense in `AbstractAuthenticationToken` because it knows nothing of a hash key. Instead, we should move this to a private method within each subclass."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `pagination_rules` in `pagination_rules`?",
      "reference": "index by memory address? I realize I don't understand why we don't just build a list :)"
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "Not part of this commit, but we thought that this may not be a good place for this url, as it is in the `/user/` namespace (effectively preventing us having a user called `lastfmscraper`, however rare it may be)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Does not appear to be used."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `bolt command run`",
      "reference": "I think this starts a new `powershell.exe` interpreter each time, which is pretty slow to run a single command. Can we just do `on(bolt, \"cmd /c #{bolt_command}\")`? /cc @Iristyle"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can we add a `collection?` method to the `VideoPage` so we don't violate Law of Demeter here?"
    },
    {
      "prediction": "I'm not sure why this is a good idea.",
      "reference": "Deleting unused code."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `assign_and_sample` and `bbox2delta` are the same as `bbox2delta` and `build_assigner` and `build_assigner` and `build_assigner` and `build_assigner` are the same as `build_assigner` and `build_assigner` and `build_assigner`",
      "reference": "`PseudoSampler` can also be imported from `..bbox`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Could you move this import to where the other `github.com/algorand/go-algorand` imports are?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'd rather not activate this protocol by default for now, unless there is a good reason for that."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure why this is a good idea.",
      "reference": "Remove these 2 blank lines."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Want to remove this?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "is this a golint requirement? huh. mixed feelings :)"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, so it's a string, so it's not a string, so it's a string, so it's a string, so it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "Generally with these tests please split up these tests so that there is a different test for each method"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should something use the lock passed in?"
    },
    {
      "prediction": "I'm not sure if you want to use `systemd:7` instead of `centos:7` instead of `centos:7` instead of `centos:7` instead of `centos:7`",
      "reference": "Is this dependant on some version of Docker? Do we need to include both or `volumes` is deprecated (or just wrong!?)?"
    },
    {
      "prediction": "I don't think the leader is the same as the leader.",
      "reference": "I know this is not new code, but should we change `leader.getState() == State.ACTIVE` to `leader.isActive(liveNodes)`?"
    },
    {
      "prediction": "I'm not sure why this is a class scope?",
      "reference": "Why not use ASTAnyTypeDeclaration? AbstractAnyTypeDeclaration is deprecated"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "A blank line at the very end of each file should eliminate the \"No EOF\" warning we see above"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "These would both be more robust with `errors.As` so that we could safely chain errors."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is checking the same condition twice?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the MPI-CUDA backend.",
      "reference": "Aren't we able to handle the case where we have MPI-CUDA without NCCL, even if it's suboptimal?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Wouldn't we want to namespace this `AA` or something similar"
    },
    {
      "prediction": "I don't think this is the case where the user has explicitly specified an AWS_PROFILE.",
      "reference": "This probably should look beyond envConfig, and include `aws.Config.Credentials` as well."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "How does this filter differ from TooExpensiveTxFilter?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the user permissions?",
      "reference": "Use \" List<String>\" instead of ArrayList<String> in declaration."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `get_object` method.",
      "reference": "we might consider hard throwing when name is None since that is explicitly not working right now and then linking to issue in the exception error message"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Just noticed this - why \"like\" and not straight \"=\""
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "is this a new test? if yes, isn't it better to check for each env var is present, and the value, instead of a count?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "when will lost exception? by my test, never happened."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You should re-stringify it here with `QUrl.FullyEncoded`."
    },
    {
      "prediction": "I don't think it's a good idea to do this, but it's not a good idea.",
      "reference": "i'm not sure why the quit channel is needed in this context"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "When `args.MemoryLimit` is empty, will `MustParse` panic?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "How soon after this will Apply() be called? It would be a shame if there was still a significant delay before a missing or superfluous route was corrected."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I add a `idx` property, and it is only use for benchmark `heap.Remove`, is it acceptable?"
    },
    {
      "prediction": "This file is not covered by the GNU General Public License.",
      "reference": "daemonic t got inserted."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This edit is non-essential."
    },
    {
      "prediction": "I think we can't use `Object.setPrototypeOf(obj, proto)` instead of `Object.setPrototypeOf(obj, proto)`",
      "reference": "Might be safer to ponyfill this?"
    },
    {
      "prediction": "I don't think this is the case where we need to check if the directory already exists.",
      "reference": "why was this join not necessary before?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Here we compare to the expected call count 3. Because 3 TermsEnum are created: it is a PrefixQuery and there is one TermsEnum created for AutomatonQuery.intersect() (the next call timeout check is skipped once), then 2 TermsEnum created for the 2 matching terms \"one\" and \"ones\"). Would it be clearer to have a separate test method? We could index more docs, for example 50 with a prefix-generated term (e.g. \"term\"+increment). There would be a PrefixQuery for \"term\", the same test code, and we would test the TIMEOUT_CHECK_SAMPLING: - 1 TermsEnum for Automaton.intersect(), and the next calls would be sampled (50/TIMEOUT_CHECK_SAMPLING=3) => call count +4 - 1 TermsEnum for each enumerated term => call count +50 We could verify call count = 54 (instead of 101 without sampling)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `--inventory` or `--global`?",
      "reference": "Add `--format` as an option. Does it make sense to have all display options available? Also need to add `--inventoryfile` and possibly the global_config_options."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `RecordException` parameter.",
      "reference": "Any thoughts on making this false by default? My suggestion is make this opt-in. Storing exception is somewhat expensive, so lets do this only if users opt-in"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "usually I do either ` IOException|RuntimeException` or if doing Throwable, use propagateIfFatal"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Wondering whether it should be `self.clone`, or `other.clone` or maybe a new `DynamicMap` declaration entirely. I see this is in the condition where `other` is a `DynamicMap`but is this definitely right in terms of `kdims`? I need to think about it more..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I chose a new category because over time I'd like to add metrics also for Authorization plugins and Auditlog plugins (all components registered in security.json). An alternative could have been `CONTAINER` I guess?"
    },
    {
      "prediction": "I don't know how to validate IotxAddressLength.",
      "reference": "IoAddrLen Golang prefers short variable names"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "PHPCR-ODM does not allow blank aliases.."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This seems trivial to forge. Can we tie this into the authentication code paths somehow so that we can really trust that the request is coming from a server instead of just some application claiming to be a server?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `Kokkos_Core_Config_DeclareBackend.hpp`?",
      "reference": "Why are you including `<Kokkos_Core.hpp>`?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "So previously health check was consuming from the normal metrics queue, now we duplicate the data to a new queue? I feel like there should be more changes to ensure the health check handler reads from the new queue? @DrewZhang13"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Yep, looks right; your new selector _should_ disqualify the rule from being XDP accelerated."
    },
    {
      "prediction": "This file is part of the documentation.",
      "reference": "cc @anurse This exists now. Kestrel currently passes the current time to all callbacks as an optimization. Just an FYI."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "remove 3.8+ f-string format to allow use in google colab"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the xstate_has_extra_fields flag.",
      "reference": "Should we assert that xstate is aligned here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "any particular reason for suppressing this change?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hot take: could this instead become `NO_DIFFICULTY_BOMB` and have` HOMESTEAD` wrap it? So this comes first then homestad with the bomb adjustment, making no difficulty the base case?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I suggest to use a scheme like \"blobvar\". \"blob\" would potentially collide if we have another API that use the blob package as a driver."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This assumes that the user has at least one listen, it should have a guard around it, because this won't always be the case"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Seems like a lot of unintended changes. Are your line break settings causing these?"
    },
    {
      "prediction": "I think this is a bug in the conda-forge command.",
      "reference": "@StrikerRUS what if we just removed build numbers and did `r-pkgdown=1.3.0`? Won't we have to fix this again if the RTD build machines change?"
    },
    {
      "prediction": "I think this is a bug in RDKit, but it's a bug in RDKit.",
      "reference": "I'm not arguing with it, but how did you decide to make this change?"
    },
    {
      "prediction": "I think this file is in the same directory as Invenio.",
      "reference": "1: D400 First line should end with '.', not 'd' 4: I102 copyright year is outdated, expected 2014 but got 2012 25:29: E126 continuation line over-indented for hanging indent 31: D103 Docstring missing 40: D103 Docstring missing 57: D103 Docstring missing 68: D103 Docstring missing 101: D103 Docstring missing 115: D401 First line should be imperative: 'Call', not 'Calls' 115: D400 First line should end with '.', not 't' 134: D400 First line should end with '.', not 'e' 134: D205 Blank line missing between one-line summary and description"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Explain that this must match the `CommonName` of the first (or is it last?) certificate in the chain, where the first certificate is the chain root CA and the last certificate is the leaf certificate."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "do we really need this behavour to be configurable?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Hmm interesting. Do the tests check out on this?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "For another PR, another `--X` candidate."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do we need to add this constant for `group_windows.go`? Otherwise, I believe the build will fail on windows. Also what do you think of adding the emoji   at the end? The windows one could be plain."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "this is a junit 3 import, not a junit 4"
    },
    {
      "prediction": "I think this is a bug in the cluster sync controller.",
      "reference": "shouldn't there be a reque expected here?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "I prefer to make it `protected set`. What do you think?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Maybe rename this to JetStreamStoreDir?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You can start by logging out the error"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "In general, what is the reason for the fallback price to be public? If it is public, why does it take baseFeePerGas instead of a block header?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "follow-up of #2002"
    },
    {
      "prediction": "I think this should be a thread pool.",
      "reference": "could you give some explanations of what problem do you want to solve by this change, and how/why it works?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "LongLivedMarshalByRefObject exists in both the netstandard and netfx xunit?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `page_ranges` option.",
      "reference": "the bridge here isn't defined as an accessor / reader to try mask it better. So you need to directly call the iVar `@bridge` here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Testing on linux with this change, containerd no longer stops when k3s stops."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Maybe [u]int64 to be consistent with other byte-valued vars in this struct?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the link to \"My Requests\", carts_path, and new_ncr_proposal_path, and new_ncr_proposal_path.",
      "reference": "This brings up the question... do we need to start assigning users to the different use cases in some way? We don't want this link to show up for Ric, for example."
    },
    {
      "prediction": "I don't think this is a problem with the `prefetch` method.",
      "reference": "Unless I'm misunderstanding something, this should just be `prefetch_(param.data_param().prefetch())`, no? That should just use the default value if there's no explicit `data_param` or `data_param.prefetch` set, removing the need to also duplicate and hardcode `PREFETCH_COUNT`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "nit : move this into a default clause in the previous switch statement."
    },
    {
      "prediction": "I'm not sure if it's a string, but it's not a string, but it's not a string.",
      "reference": "It should be return \"''\"; I will fix it"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "Go standard linter hates `Id`s and likes `ID`s, please do not resist."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `fetch_ref` command.",
      "reference": "I don't think retrying here is as useful, since `git-checkout` doesn't access the network AFAIK, and if it fails once it's probably going to fail all three times."
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "Fixing this typo caused a build failure in `cmd/ctl/pkg/status/certificate/certificate_test.go:238` Could you also update it there?"
    },
    {
      "prediction": "I think this is a hack, but I don't think it's a hack.",
      "reference": "Please note that adding this will import `extension_condition` in the entire scapy (as you are located in a layer). You might want to move this inside the RTP class ? Would be better i think"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This will need updating, as I'm not sure we'll want to turn on random ordering if they've specified a seed for programmatic use."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Are you sure these are all client libs? This seems fragile: if we later load sthg else early this will break. Seems best to have some kind of sanity check: at least add an assert in the current location where this is set."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Picking nits here, but as a Dictionary already is a collection of KeyValuePairs there's undoubtably a way to code this that doesn't involve constructing any new ones."
    },
    {
      "prediction": "I don't think this is a bug in the CMMN model.",
      "reference": "As Miklas stated, please avoid wildcard imports."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe change it to `module.exports = server` ? Becase there's nothing else to export here"
    },
    {
      "prediction": "I don't think this is a bug in knative-gcp.",
      "reference": "This may be an automated change, but the import seems to fit better where it was previously."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Might we want to separate including this snippet and sending the data for signed in users into different partials?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "closest to the address"
    },
    {
      "prediction": "The `autoRowSize` option should be `true` or `false`.",
      "reference": "It should be much more clear for end-user  "
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Isn't this an example that this will be prone to false positives ? We had nothing to fix in the codebase (And I think there is dict that could be named tuple in the MessageStore/MessageIdStore), but we have a false positives on our checkers."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "We control `octest`, so it shouldn't be necessary to provide struct literal keys. This is a case of vet being too picky."
    },
    {
      "prediction": "I'm not sure if this is the default plan visibility.",
      "reference": "I would put that constant under config/initializers/constant.rb and I would leave application.rb for rails specific."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Is there a reason not to do something like `if _, ok := doNotUnref[ptr.ID]; ok { return ops }` here?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `w3c` option.",
      "reference": "This would return a tuple of two dictionaries. You need to combine them and return a dictionary"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `__call__` method.",
      "reference": "Why not always forward it to `_data`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `refresh_spotify_token` method.",
      "reference": "there are tests that use `client.get` which will fail now"
    },
    {
      "prediction": "I think this is a bug in libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs/libkbfs.",
      "reference": "Whoa, TIL about this syntax."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This is a smell. When is this valid? Perhaps this should be `nil, nil, ErrNoResponse` or some such. While it is usually invalid to have neither a return value or error, we rarely check for the case in other idiomatic Go. Nothing wrong with extra defenses here, but think about it."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "This URL is outdated, add a `TODO` to fix it."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`ChainID()` is a getter method, move up to `Nonce()`"
    },
    {
      "prediction": "I think this is a bug in the scheduler.",
      "reference": "If this condition is not met, shall we just throw the exception rather than logging it? @li-ygerchikov Your thoughts?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "nit: alpha-sort `ruamel.yaml` in this list please"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Remove this because we already added it in another pr"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Can we maybe move the `File` creation to a new method? I mean both changes look equal to me with the difference of two parts, which could be specified using two input parameters."
    },
    {
      "prediction": "I don't think this is the right thing to do with `access_token`?",
      "reference": "I think we want to require the association with the user...?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "I am unsure the below implementation is correct, but need this method to not panic else it borks the chain-validation tests."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: no need this change anymore."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This isn't really that closely related to everything else in this PR, but I'm pretty sure it's a correct change. I'm not familiar enough with the taint feature to know how to test it, but I worry that without this change some of the taint stuff might mess up the `parent_nodes` for a reference."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "[Checkstyle] ERROR: Unused import - javaslang.collection.Stream."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "The numbers were changed since now _root_ is also added to the doc, increasing the field count by 1."
    },
    {
      "prediction": "I don't think this is a real call, but it's not a real call.",
      "reference": "TTemplateParamClass is handled above with the same content in the conditional"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Do we need to add `theme` here?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "i think you have to regen the api stuff, `make generate`"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "DataHash shouldn't be needed here"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`info` was chosen deliberately to mirror the old behaviour that users expected."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "For some reason, Safari handles ember arrays differently than Chrome/Firefox. To get around that, we cast the ember array to a regular array to verify the deep equal. (Note: I tried wrapping the expected value in an emberA - which would look like `expect(someEmberArray).to.deep.equal(emberA(['a', 'b']));` but that didn't work either)"
    },
    {
      "prediction": "I think this should be the original type of the vector, but I think it's the original type of the iceberg type.",
      "reference": "`icebergType` indicates the corresponding iceberg type of the `FieldVector` `originalIcebergType` indicates what the real type we will read from the `FieldVector`. For example, the parquet int backed decimal, the `icebergType` should be integer, `originalIcebergType` is decimal. I intend to only keep the `originalIcebergType`, but listening to your ideas."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "The double (and thus triple as seen below) pointer gives me pause. I could imagine providing some larger API surface to smooth it out, but it's likely not worth it."
    },
    {
      "prediction": "I'm not sure if this is a problem, but it's not a problem.",
      "reference": "The test name as written was grammatically correct, but now it isn't. Both 'MongooseError' and 'instance' should be both singular or both plural."
    },
    {
      "prediction": "I don't think this is the default value, but it's the default value.",
      "reference": "SmartStoreInspectorTest was throwing a NPE here"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We prefer line wrapping that keeps arguments to the same method aligned rather than aligning arguments to different levels. Here, the lambda to create an `InternalRecordWrapper` is an argument to `transform`, but it is aligned with `deleteSchema.asStruct()` that is an argument to the outer `toEqualitySet` call. Instead, can you add a newline for each argument to `toEqualitySet`? If the line with the lambda is too long, then you can also add a newline for it that it indented from the start of the line with `transform`, so it is clear that it is an argument to `transform` and not `toEqualitySet`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think it would be a good idea to wrap this in an if like the stats above, just in case."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "@angmas1 just make one more change here too. Move the else line to the line above it, where the if block ends and remove the braces like in line 280."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Looks like the actual rename is missing in this commit edit: Arf, nevermind, I was at the wrong commit  "
    },
    {
      "prediction": "I don't think this is a problem with `opts.getAssemblyOptions`?",
      "reference": "I'm a little stuck understanding, how would this result in an error when `this.opts.params` is not set? It will just not do `AssemblyOptions.validateParams(this.opts.params)`  "
    },
    {
      "prediction": "I don't think this is a good idea to use `regexp.MustCompile` instead of `regexp.MustCompile` instead of `regexp.MustCompile`",
      "reference": "networkVarPattern (etc) then?"
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the case.",
      "reference": "I think it makes sense to do `metadata[:block].clone`, as thats what `new_metadata` is, but somehow it's missing the block from its clone."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Just realized this should be fixed instead of changing here. Concatenating int should still result in lowercase string."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `firefox` or `marionette`?",
      "reference": "For Se 3.x we shouldn't need to specify `marionette: true`? I'll see if I can figure out where this is getting used that it might be necessary here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should be renamed to `chain.Store`. It was named `DefaultStore` as an alternative to `StoreImpl`, which is the (bad) Java convention."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "ad.Source is disk name? Shouldn't the order of initialization be reversed here then? First set ad.DeviceName, if it's empty, set ad.Source? Or this is a different use case? This is the third place where this device/disk default logic is implemented, so another reason to move it to regAttach, if it's possible to be generalized."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "typo: \"be hold\" -> \"be held\""
    },
    {
      "prediction": "I'm not sure why this is the right value?",
      "reference": "I do not think we should have any logic inside the null storage. 1 has a very specific magical meaning. We should either return null here or long.maxValue."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why did this change?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Removed this method. Doesn't seem to be used in the code, and the variable set here doesn't seem to be used in the views."
    },
    {
      "prediction": "I'm not sure if this is a property bag dictionary. I'm not sure if this is a property bag dictionary. I'm not sure if this is a property bag dictionary. I'm not sure if this is a property bag dictionary. I'm not sure if this is a property bag dictionary. I'm not sure if this is a property bag dictionary. I'm not sure if this is a property bag dictionary. I'm not sure if this is a property bag dictionary.",
      "reference": "Remove the initializers (\"`= null`\") from both parameters. Remember that that's why we added the overloads: to ensure that all languages could have the convenience of the abbreviated argument lists (not all languages understand default parameters)."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "I think you can just remove most of these attributes outside of `ElementType()`. Instead, this should expose the arrow array. We're not going to use these methods anyway."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `createComponent` or `collectComponent`?",
      "reference": "Thinking this should be `removeNode()` exported from `dom/index.js`. Thoughts?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Does this need to be saved in the state file? Or are we recomputing when the task is read from the state file?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Looks like `s.inserts` and `s.removes` are updated under sublist's lock, so I don't think you need atomic for those 2."
    },
    {
      "prediction": "This is a hack.",
      "reference": "@TD-er use bitRead/bitWrite macros, do you use here inversed logic?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `fetchMock` and `fetchMock` and `fetchMock` in `fetchMock-jest` and `fetchMock-jest`",
      "reference": "The previous `fetch` mock was exposed globally before - can we do the same with `fetchMock` so we don't need to import it in every file?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is ExpectData still used anywhere?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do you want to allow the character `.` or any character? Because inside a regex `.` means any character, if you want to authorize `.` then you need to add `\\.` ."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `mongoose.Schema.post('find', (result) => { assert.ok(Array.isArray(result)); });",
      "reference": "`eachAsync()` should pass a doc, not an array of docs, to the callback. This would be a massive breaking change."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "please start log with caps letters"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is this where we want it in relation to the other scripts?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please wrap this variable within a self invoking anonymous function. (function(){ FEATURE_NAME = \"reports\"; //and rest of the js goes here. })();"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Haven't tried, but what happens currently if `-f` is used and it's not running? (thinking: `-f` should ignore the case and just proceed?) I see we have a special case for `all`"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "no need for custom errors in tests unless the tests are intended to mock a specific sort of error"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This const has already existed in the code, no need to define a new one"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would Errorf be better than Warnf?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "A good candidate for StringBuilder? Also make sure to add white space around the operators (`path + \"/\" + file`)"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the right thing to do.",
      "reference": "Can we have the same argument order as `getUploadedFlowFile`?"
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "this dynamic config should still be valid, i.e. operator should have the ability to control each individual task queue just in case"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should these cases be logged? `if not obj` used to be"
    },
    {
      "prediction": "I'm not sure if this is the case for apt-key list.",
      "reference": "Is it OK to assume that keys.gnupg.net has the new key?"
    },
    {
      "prediction": "I'm not sure why this method is optional.",
      "reference": "A note for however is curious. I think these two notes add negative value only. In general we want people to implement this method (in particular after this patch). If we leave these old (and currently mis-rendered) notes, file system implementors might not implement this method referring to this."
    },
    {
      "prediction": "I think this should be the same as `toSortedQueue(comparator)` and `toPriorityQueue(comparator)` and `toPriorityQueue(comparator)` are the same as `toSortedQueue(comparator)` and `toPriorityQueue(comparator)` and `toPriorityQueue(comparator)` are the same as `toPriorityQueue(comparator)` and `toPriorityQueue(comparator)` and `toPriorityQueue(comparator)`).`",
      "reference": "Comparators (or functions in general) cannot be compared for equality. Therefore `PriorityQueue.of(comparator, ...)` always has to return a new instance."
    },
    {
      "prediction": "This is a hack.",
      "reference": "It's a little surprising that CachedThreadPool overrides the max_threads argument. This makes sense as a solution though."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "```python # if avg_factor is not specified, just reduce the loss if avg_factor is None: loss = reduce_loss(loss, reduction) else: # if reduction is mean, then average the loss by avg_factor if reduction == 'mean': loss = loss.sum() / avg_factor # if reduction is 'none', then do nothing, otherwise raise an error elif reduction != 'none': raise ValueError('avg_factor can not be used with reduction=\"sum\"')"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`padding` should be 0 instead. Actually you can just remove padding and dilation to use default values."
    },
    {
      "prediction": "I'm not sure why this is the right place for this class, but I'm not sure why this is the right place for this class, but I'm not sure why this is the right place for this class.",
      "reference": "$balance is initialized to 0 above in line 1428 and then assigned in line 1437. If we're no longer manipulating that value, is there a reason to use a variable at all? It might make the overall code less confusing to make some changes there."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we need to explicitly use keyword arguments?"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Might still want to log this as `TargetBuilding` but with a slightly different message?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "ref. above, this also can be omitted in case `txt = std::move(other.txt);` could work (or copy), consider `std::array<String, VARS_PER_TASK>;`? or a custom object implementing `Object& operator=(Object&&) noexcept;'"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Well done, we forget that one apparentely."
    },
    {
      "prediction": "I don't think this is necessary.",
      "reference": "Guess it isn't used. The dask thing was just a prototype so removing it is probably the right thing to do."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `os.getenv(\"CONTENT_INDEX_EXTS\", \"\").split(\",\")` instead of `os.getenv(\"CONTENT_INDEX_EXTS\", \"\").split(\",\")`",
      "reference": "This code is correct, but it's a bit confusing to see how (e.g., without the if startswith(\".') the or below would break.) I think it will be clearer for the long run if you refactor this just a bit. CONTENT_INDEX_EXTS (all caps) looks like a constant, but is now being set by the environment. Instead, replace the reference to CONTENT_INDEX_EXTS in index.py with a simple call to a method \"get_content_index_exts\" (or similar). Then you can write all the logic into one clean function."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "please update the zms conf file to have a small description of these options since by default feature is off and must be enabled"
    },
    {
      "prediction": "The `lazy` option is mutually exclusive.",
      "reference": "Should be `this.opts` instead of `defaultOptions`"
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's a string, but it's not a string, but it's not a string.",
      "reference": "You can reuse `USERS` above as well."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Whoa, was this opto breaking something? I guess if this final path is filtered out, we still need the queue? Have you run the suggest benchmarks to see if removing this opto hurt performance?"
    },
    {
      "prediction": "I'm not sure if this is a List<T> or Stream<T>?",
      "reference": "I'm not sure about this, please check the usages. It's only used currently to reverse it, maybe we should eliminate this method completely instead."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Since this is only used in the MyResearchController, does it need to be placed at the AbstractBase level?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "why `PhaseSelector` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does` AllowlistedModules` have the same meaning of `WhitelistedModules`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I missed the $preserve_keys=true case when adding this to Phan. For psalm, two separate signatures may make sense"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "TcpServer will be created for each HighwayServerVerticle instance so the counter number in server is not correct."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Why change this from a foreach? I can't see it gaining anything here and code styles shouldn't change just for the sake of it."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I'd say \"cgroup2 hybrid path\" instead."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I dont see a reason to print URI for `Target`. we do not expose that in inventory v1"
    },
    {
      "prediction": "I'm not sure if this is a boolean singleton, but I'm not sure if this is a boolean singleton, but I'm not sure if this is a boolean singleton, but I'm not sure if this is a boolean singleton, but I'm not sure if this is a boolean singleton.",
      "reference": "Do we still need this?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`campaignSource` is unused (from `structcheck`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "we should discuss how to not hard-code this version"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `cursorOptionNames` instead of `cursorOptionNames`?",
      "reference": "do we have a doclet for this event?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why don't we want to catch segfaults by default?"
    },
    {
      "prediction": "I'm not sure why this should be done in the future.",
      "reference": "You could probably dispose request & content if you `await` the SendAsync."
    },
    {
      "prediction": "I'm not sure if this is a test case, but it's not a test case.",
      "reference": "why is this test case here? this file is for testing functionalities in utils.py"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "why do we have an env var for this? not sure why we'd want to suppress welcome emails but not any others"
    },
    {
      "prediction": "I think this is a bug in the source code.",
      "reference": "drop the todo?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Maybe use { } here like we are most other places now."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I want to get PartitionData field type, I don't know how to get it in other way."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `withPendingRewards` flag.",
      "reference": "I think that a single `Get` method would be preferable, that would have the following parameters: Get(addr basics.Address, withPendingRewards bool, cidx basics.CreatableIndex, ctype basics.CreatableType) where we ignore cidx of -1, and adding support for ctype of \"AssetParams\" or something like that. (i.e. so that this Get call would be good for asset holding/asset params and applications )"
    },
    {
      "prediction": "I think this is a bug in HIVE_DEFAULT_NULL_STRING.",
      "reference": "This can handle the '\\\\' problem, but if (not possible) the user define '\\\\' as null, this logic will break. So here, it should be to compare the whole HIVE_DEFAULT_NULL_STRING, and make sure length is equal, as I understand. \\N is NULL, but \\NA is not NULL, what will happen if there is \\NAA ?"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Hmm, I would think that anyone who can edit the request should be able to delete the observation, in case they accidentally add the wrong person or something."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `publicly_visible` property.",
      "reference": "I know we are doing this other places already. It would be good to refactor this and the paginable publicly_visible so that we are DRY. Can wait until after MVP though when we do general cleanup"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think this should read \"is always observed before\" or \"is never observed after\"."
    },
    {
      "prediction": "I think this is a bug in the Apache License, Version 2.0 (the \"License\");",
      "reference": "You might consider adding yourself as an author of the class."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If this fails, then 'stderr' is not a valid file handler anymore, and then any further 'write' operations will fail. Maybe some handling of such situation should be added here?"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Break out tests for events into their own tests rather than placing them in other ones. That makes it easier for us to figure out where problems lie and to do a TDD-driven implementation over new APIs."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think your indentation is wrong here."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "UT spotted that we weren't marking routes dirty when they targeted at Node and that node's IP changed. e.g., the case where a WEP appears in the syncer before the corresponding node does, so we don't know the node's IP. I added a new map to track the CIDRs for each node so that when the node IP changes we can mark those CIDRs dirty. Right now it's only used for the \"WorkloadIPs\" scenario. Need to decide if the same issue applies in the \"CalicoIPAM' case. I suspect it might. It looks like we have some logic present to detect when our own node IP changes, but we don't seem to handle when a remote node's IP changes."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `openssl` library.",
      "reference": "Given this will 'pause' bolt for a few seconds on older rubies, perhaps emit a debug message saying \"Warming up OpenSSL\" or something to that effect"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Initializing _format to None, but asserting that it's not None later, seems unnecessarily fragile. We shouldn't architect the package class to rely on classes or methods that use it (e.g., build). Let's at least set the format to the default in case we don't create all packages through build.py."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This change should also probably go into the corresponding method of the abstract By class?"
    },
    {
      "prediction": "I'm not sure why this is a constant?",
      "reference": "Should this be set to something else?"
    },
    {
      "prediction": "I'm not sure how to do this? I'm not sure how to do this? I'm not sure how to do this?",
      "reference": "Whats up with this? It looks like this is rendered on purchases/new for subscribers, so it would result in a dead end?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Glad to see this generalized to support the backend argument."
    },
    {
      "prediction": "I don't think this should be done in the future.",
      "reference": "`ctx` is unused in ListDeploymentChains"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd say the format like `\"xxx: %w\"` is more convention when wrapping an error basically. You refered to anything like this?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This seems relatively high, is it the recommended value from the etcd folks? Or is this debugging cruft?"
    },
    {
      "prediction": "I don't think this is a good idea to use `peertracker.WatcherFromContext(ctx)` instead of `peertracker.WatcherFromContext(ctx)` instead of `peertracker.WatcherFromContext(ctx)` instead of `peertracker.WatcherFromContext(ctx)` instead of `peertracker.WatcherFromContext(ctx)` instead of `peertracker.WatcherFromContext(ctx)` instead of `peertracker.WatcherFromContext(ctx)`",
      "reference": "This requires updating the name in the `endpoints` tests, please run `make test`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "LOG(FATAL) means coredump, LOG(ERROR) is better here."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "/javascript/firefox-driver is the Selenium implementation of a WebDriver for Firefox. Since it generally isn't W3C compatible, it shouldn't change. We can just drop this change."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It's a bit weird to have `svc.go` to include a `ScheduledJobType`...should we rename this file?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "For some reason `protoc` doesn't copy license header from `proto` files to generated code. But this code will never be checked in, so it is ok."
    },
    {
      "prediction": "I don't think this is a bug in the database, but it's a bug in the database.",
      "reference": "I don't know what the implications of this change are for pumps other than the insight but i would add `|| trList2.get(0).pumpId == temporaryBasal.pumpId` in case we see the same pump event again, in order to not duplicate it in the database."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "is there anything still referencing `checksumAddress` or can we just delete it?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The reason I didn't suggest it before is because I didn't want alerts for every tried - but not updated provision, but I can see a value in it from OSD perspective"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe Key is not necessarily nil, it could be empty string. Probably better check a.Kind == Create"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `cancellationToken` parameter.",
      "reference": "This is only used for headers and therefore isn't used."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Wouldn't it make sense to add a files_import_command and a db_import_command, which could be empty? I guess that leads to potential backward-compatibility problems, but it's worth thinking about. Perhaps add an import-api version to solve that? Overall, I think the actual db import logic and files import logic should be moved into the yaml file. What you you think of that?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `ast.BaseNode` or `ast.BaseNode`?",
      "reference": "Why do we have this here? I'm not concerned about it really, just curious."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "@justicz Why are these switched here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe verify that an anchor was created -- that the markdown was processed?"
    },
    {
      "prediction": "I think this should be an abstract class.",
      "reference": "Is this just a minor improvement or is it necessary? If just some minor improvement, I recommend you don't touch Lucene in a Solr PR."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the client.",
      "reference": "why delete this method?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Does this transform only the `MethodContext`, or also the `OutputContext`? (Looking at the other files, I gather it's the latter.) Might be helpful to mention that here."
    },
    {
      "prediction": "I think this file is not used in the GNU General Public License, version 2.0.",
      "reference": "Could you please clean-up this line while at it?"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string.",
      "reference": "no need to use a pointer. Just string and check for != \"\""
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "this means h2 mode? but how h2c can work?"
    },
    {
      "prediction": "I think this is a bug in the GNU General Public License. I think this is a bug in the GNU General Public License.",
      "reference": "This line should not be there"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "why do we need lock here? if needed, then we also need to lock in Start()?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to add a task to the dispatcher.",
      "reference": "this should be on default-switch, uhm? else you will handle twice (c++ and lua). I'm just saying..."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "unrelated minor fix"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `npm config set strict-ssl false`?",
      "reference": "can you add `, echo: false` to the end of this as well. I don't think we need to echo this to the log. You might need to update the spec as well."
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "This test does not really verify that we're doing the correct thing now, is it? It seems to pass with and without the patch."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should just be able to defer the call directly here too"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this a magic number? I assume this makes it look better."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Would welcome a stringification method on big.Int in specs-actors"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "PersistBlockLevelInfo -> UpdateBlockLevelInfo"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Type is redundant since it is inherited."
    },
    {
      "prediction": "I'm not sure if this is a view.",
      "reference": "better use `!isView()` so that we don't need to modify multiple lines in future."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I know you don't usually open up the singleton class, but I was getting a `private method called` error when trying to use `self.attr_writer` - any idea?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `canRate` method.",
      "reference": "There's no need to create a new variable here, the other checks just use the item type directly."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `self.workshops` and `self.videos` where product_type: 'video'",
      "reference": "Any other possible names? Feels like going with \"workshop\" for this product_type could increase the confusion between course/workshop in the codebase."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@eugene-manuilov Isn't this already taken care of by `fetchGetURLChannels` via `createFetchStore`? Why is the extra `receiveError` call needed here? (This was already in the IB, but just struck me while reviewing here.)"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "nit: should go before `grpc`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not using the Cancel? I thought cancelling a \"parent\" context would cascade to \"children\" contexts, cancelling them as well. In short, how does cancel work?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Could you explain why we default to binary now? It seems it's safer to default to text to avoid stuff getting executed or parsed by browsers accidentally. If we need to add support for particular types, we can add them explicitly right?"
    },
    {
      "prediction": "I think this should be a string, not a string, but it's not a string, but it's not a string, but it's a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string.",
      "reference": "Bit worried about the prefix since this seem to be being used for non-Openstack data too (host endpoints). Should we just leave host endpoint status at the old path (or remove it since AIFAIK, it's not used anywhere)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This might be a silly question, but what happens to files with durations > 24 hours?"
    },
    {
      "prediction": "I'm not sure if this is a static method, but it's not a static method.",
      "reference": "`AddDiagnosticSourceInstrumentation` method can now be eliminated and simply use `AddInstrumentation`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think we also need to add `name:` to the bolt-project.yaml files in `spec/fixtures/projects`."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "worth mentioning the same warning here as in `md_util.go`, I think."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Do we need both the checks, for `Items` not nil and `len(Items)`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do you know what this is coming from? It keeps getting deleted/created @nickbristow"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: leaving these in place would have reduce the number of files that this needed to touch, and avoided a possible problem removing public fields. I don't think it's worth blocking for this change, but we like to keep patches as small as possible by not breaking references like these."
    },
    {
      "prediction": "I think this is a bug in EasyAdmin 1.x.",
      "reference": "`The %s is deprecated...` -> `The %s method is deprecated...`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "No, it wouldn't go there because that code won't reference or enforce it. Here is ok for now."
    },
    {
      "prediction": "I think this is a bug in the cross-plat engine.",
      "reference": "How will we show that test run aborted (because of a crash) if we don't set aborted to true?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: Might as well make this same change to AdaptedPipeline."
    },
    {
      "prediction": "I'm not sure why this is the right thing.",
      "reference": "Just to clarify: I see that only the hive2 withZone object inspector is changed. Does that mean that the predicate pushdown problem only occurred on hive2?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Based on username requirements for forge.puppet.com - only letters and digits permitted."
    },
    {
      "prediction": "I don't think this should be true, but it's not a problem.",
      "reference": "Was this removed to ignore the extra columns coming from the file projection?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please can you pull out the shared function into a shared file? I think that'd be pretty easy to do for this module. I think you could: - pull out a function `configureSyslog` that is implemented on Linux, but stubbed on Windows - pull out a function `openLogFile` that is implemented differently on each - share everything else"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Instead of hardcoding the AWSEmailProvider here, it should come from properties, so that it can be replaced with another EmailProvider for ZMS vs ZTS"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `account.login` instead of `account.email_confirmation` and `account.password_confirmation` instead of `account.password_confirmation`",
      "reference": "+1 for creating this script to help people get boot strapped"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you need the prefix?"
    },
    {
      "prediction": "I don't think it's a bug in this case, but it's a bug in this case, but it's not a bug in this case.",
      "reference": "if retcode is < 0, it should return -1 indicating an error."
    },
    {
      "prediction": "I think this is a hack, but it's not worth it.",
      "reference": "Are those necessary? I feel like `useless-suppression` could be avoided here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `AudioBitDepth` and `AudioSampleRate` properties. I'm not sure if this is the right thing to do with the `AudioBitDepth` and `AudioSampleRate` properties. I'm not sure if this is the right thing to do with the `AudioSampleRate` property.",
      "reference": "Is this equivalent in JavaScript?"
    },
    {
      "prediction": "I think this should be a bug in the future.",
      "reference": "get/list operation is not schema change, it is supposed to use VLOG"
    },
    {
      "prediction": "I think this should be a `ReadOnlySpan<KeyValuePair<string, object?>>`",
      "reference": "we'll need to delete this whole file, right?"
    },
    {
      "prediction": "This is a hack, but it's not necessary to change the isolation level of the table.",
      "reference": "\"this table hasn't mutated within this transaction\" may sound like implying that if this transaction contains table mutation changes, `refresh` may have impact, which I think is not true? I guess what you were saying was if other transactions committed to this table successfully when this transaction is half way through, refresh in this transaction will still return the same state as when this transaction begins."
    },
    {
      "prediction": "I don't think this is a bug in the future, but it's a bug in the future.",
      "reference": "Can we move these into some kind of experimental API group? I don't think we want to call them `v1` just yet :)"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "  I think this makes a lot of sense but we may want to highlight the change for people doing UAT in case the ordering of sections is off anywhere when customizing or using the drag-drop feature"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "These files should in `/javascript/brython`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I'm not sure this is the right fix - I'd be more happy with a `continue`. That way, we don't enter the code at the bottom of the run loop (e.g. sending packets). Keep in mind that this error here may be triggered by a peer doing something security-relevant, so I don't think we should do much more work other than sending the close frame."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we fix this, or is it going to stay broken."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is there a reason to remove this attr?"
    },
    {
      "prediction": "I don't think this is the default message layer.",
      "reference": "log message should be started with upper-case word."
    },
    {
      "prediction": "I don't think this is the default size of a chunk.",
      "reference": "I guess this is not needed anymore now?"
    },
    {
      "prediction": "I think it's a bit of a hack, but it's a bit of a hack.",
      "reference": "I think I would prefer retaining the argument. It's true that we are not using it now, but it's harmless, it's good to have a constructor function that accepts all the field values as arguments. Performance-wise, it does not matter."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Is this a different fix?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Why not add a `EnterNS` filed instead of `WithoutNS`?"
    },
    {
      "prediction": "I don't think this is the default value for `trueOrFalse` and `falseOrFalse`?",
      "reference": "Same points as in other test file."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I have a PR pending, can you change this bit index to `16`?"
    },
    {
      "prediction": "I think this is a bug in JavaParserInterfaceDeclaration.",
      "reference": "we should probably have some utility class for this sort of things"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "Curious that I'm not seeing any occurrence of the new error check in this file. Why was it disabled?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "does it return something?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This function is also called in various Site Kit module components, where the error object (here `data`) also needs to be passed, otherwise the link to fix the issue won't appear."
    },
    {
      "prediction": "I don't think it's a string, but I don't think it's a string.",
      "reference": "super nit: `revision string` (the passed value might not be a SHA hash)."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "@snakefoot why is internal needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why were we disabling health checks before?"
    },
    {
      "prediction": "Should we remove this?",
      "reference": "did `conftest.py` actually show up for you? `test_files` should never contain it..."
    },
    {
      "prediction": "I don't think this is the case where the schema name is reserved.",
      "reference": "Should this be a ! on line 565? I would have expected the condition to be similar to line 564. If I am wrong please excuse my mistake."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please change to `1070400`. I promise to look into this PR in more detail before the 1.7.4 release ;)"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Can we change to use `LogicalType.getChildren`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'm confused as to how these are both passing."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the current user?",
      "reference": "Prefer single-quoted strings when you don't need string interpolation or special symbols."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "there is `\"` sign in commit message and colon. can you rename also `descrition` to plural `descriptions` and add there `$` ?"
    },
    {
      "prediction": "I think this is a bug in TelemetryInterceptor.",
      "reference": "timerNoUserLatency is not being used?"
    },
    {
      "prediction": "I don't think it's a string, but I'm not sure if it's a string.",
      "reference": "@lmazuel - I've made a couple of minor changes to serialization.py, if you could do a quick review :) They should not be breaking, and I doubt are used by the existing clients so may not need a new release yet. Effectively it's a change to support default/constant date and datetime values by allowing strings to passed in instead of date or datetime objects. The strings would need to already be in the correct ISO formatting that the request will serialize to. Let me know if you think this is okay."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Why change the name in the XML?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `after_update :when_org_changes?` method.",
      "reference": "This is much cleaner. makes it easier to tell what happens on a save."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Could you add return error unsupported operator here  "
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "(Mhh, we seem to use different formatters - we should unify them. I like the wildcards)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should `kind` be a command line parameter also?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can we have it inside FromAccessList?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why not embed filterASCII in this function?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I am curious, shouldn't \"currentContinuousFlowProcessed++;\" be added right after line 1873? otherwise we will count 1 extra when a exflow wakes up from the sleep section,.even though it hasn't been assigned"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `isinstance(e, configtypes.BaseType)` and `isinstance(e, configtypes.BaseType)` instead of `isinstance(e, configtypes.BaseType)`",
      "reference": "You can probably move this up after the `._Numeric` line."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@Tarrasch this is another change you need to pay attention, it seems `SGEJobTask` is not calling `super.__init__` which break the test case some how."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Do we need indices for this table?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "what about making this function static inline to avoid the extra declaration ?"
    },
    {
      "prediction": "I don't think this is a bug?",
      "reference": "I forget the difference between type definition with \"=\" and without \"=\" again, but can we unify the style? I believe the difference doesn't apply to TableIDType and GroupIDType whatever it is?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "would be `DEPRECATED Percentage of the graph (in vertices) to contract [0..1]` better?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "These command names are specific to Chromium-based browsers. Please move to `ChromiumDriverCommand`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "if we won't use, should we remove this?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Having 2 items with the same key (Mvx) won't work in a dictionary"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "@cpytel how does the flow work right now? I expect to go to the sign up as customer page after putting in my code, but it goes to the longer landing page?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`event_msg` has the same size (1024) as a `message`. Maybe should be increased to 2048 instead? Then this `\"[error] %.512s\", message` could be changed to this: `\"[error] %.*s\", sizeof(message), message`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Nit: unnecessary whitespace change."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hit a flake here where I think there may have been some output to stderr that got mixed in with the output from Stdout. Hence switching to `Output()`, which does also capture stderr as `err.Stderr`"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "I would use static_cast<label_t>(0) and static_cast<label_T>(m_num_labels) just in case."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Even if we want to keep in original case - domain will be lower-cased."
    },
    {
      "prediction": "I'm not sure why this should be done here.",
      "reference": "Based on discussion with Chad it feels like trail_map_json could be a good column name."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This array should be logic-less, just the language string (without `Lang::get()`) should appear. Then `trans()` is [or should be] used when the balloon selector renders the values."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This looks like it runs both pre 3.0 rake tasks and 3 rake tasks, and since pre 3.0 we didn't use bundler, my guess is it will fail then."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure the replacement is a good idea, and as I said in #336 , this \"parent-name.scope\" is not a good idea in the first place, specially when we support assigning a slice as the parent, so we should change this, WDYT?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "sloppyReassign: re-assignment to `err` can be replaced with `err := kv.WriteBatch(batchForBlock)` (from `gocritic`)"
    },
    {
      "prediction": "I'm not sure why this should be done in the future?",
      "reference": "using factory method. return CompletableFuture.completedFuture"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "The `_x` function needs to be imported at the top of the file (in addition to `__`)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "this looks like the only controversial change potentially. @MatthewHinton56 Could let us know why you made this change (which `go vet` warning was triggered)? @wenyingd could you take a look and let us know if you're okay with this change?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the user control.",
      "reference": "This seems like left-over debugging code. I think I fixed this to no longer be necessary, switching to UserControl for the designer."
    },
    {
      "prediction": "I don't think this is a bug in moto.elbv2.",
      "reference": "As we're currently not applying any logic in the proxy listener, I guess we can simply remove this file (and remove the `listener` argument from the `register_plugin(..)` call above)."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Isn't the point of the clock module to encapsulate access to `time.Now()`? Coming later?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "as before - if you've set this, you should be able to get rid of the `os.Setenv(\"ALGOSMALLLAMBDAMSEC\", \"500\")`. make sure that the various tests still takes have the same execution time."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Pretty sure the single quotes here should be double quotes, single quotes are not expanded by the shell."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's not a string.",
      "reference": "these are not really constants, right?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "import below copyright statement"
    },
    {
      "prediction": "I don't think this should be the same as `customer_should_receive_receipt_email` but it's not the same as `customer_should_receive_receipt_email`.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure if this is a string or array?",
      "reference": "`if (is_string($value) && $this->getDefinition()->get('allow_html')) {`"
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, so it's not a string, so it's a string, so it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's not a string.",
      "reference": "I think we have the same problem here - if folks called the `public void Add` with a `null` key, we need to use `Guard`."
    },
    {
      "prediction": "I think this is a bug in the RDKit source tree.",
      "reference": "I thought that the main was in catch_qt.cpp?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would rename the field to IMAGE_TYPES and make it an array. I don't think we need list operations. Also, if possible, I would move the field to the ApiFields class. What do you think?"
    },
    {
      "prediction": "I think this should not happen.",
      "reference": "I'd prefer to timeout on this, but I know it's not a pattern that is being followed"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "hmm let's not use * imports please"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "is this configuration key already exist in prometheus ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "As @gravitystorm said new tests need to be using factories, not fixtures."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You can replace IP by hostname."
    },
    {
      "prediction": "I don't think this is the right thing to do with the HID usage page.",
      "reference": "This should say \"why\" NVDA should do things in this order."
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "nit these will get changed back during next release."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "it is actually not needed to make the member public. the build tags can also set a package scoped variable."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "We already have a method for it 'icon' => $content->getIcon()"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Instead of importing `golang.org/x/net/context` The SDK should use `aws.BackgroundContext()` instead of `context.Background()`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think this is an agnostic change for the ORM right? Why was it doing this? - this does not work on PHPCR-ODM as the `id` is not a field - although I guess it could be mapped as such."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'm not 100% sure, but I think this should be `explorable`. If not, I think `explorable` can be removed entirely."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Note to self: Why was this not originally not using `stderrbytes`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is betterLOG_IF(ERROR, status != 0) ?"
    },
    {
      "prediction": "I don't think this is a test case, but it's not a test case.",
      "reference": "I wouldn't call it default too."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Why disable the rule for this file?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Thanks for adding this :+1:. Could you please move it to go after the `ctaLink` prop?"
    },
    {
      "prediction": "I don't think I want to use `IEnumerator.Current` here.",
      "reference": "The other way around Current can be null."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "why does it have to be here? Due to breadcrumb navigation?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I fear moving this to some common func. We are swallowing the error here. This might be ok in UT but not in actual source code."
    },
    {
      "prediction": "I think this is a bug in pytest.py.",
      "reference": "Please don't use \\ as a line continuation. Do an implicit string join instead with parens: ``` (\"Message ...\" \"and ...\")"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "there needs to be a change here. setting up the batchstore with localstore.Unreserve hook"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "I think if we can provide a more convenient method to add configs . e.g. public static void addConfig(String k, Object v)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "line is 165 characters"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please add a copyright notice. Also, could you tell me please why do we need this empty provider here?"
    },
    {
      "prediction": "I don't think this is the case, but I think it's not the case.",
      "reference": "I feel like this would be easier to read if we join the two if's together: `if (maybePrivacyGroup.isEmpty() && !privacyController.isGroupAdditionTransaction(privateTransaction))`"
    },
    {
      "prediction": "I don't know why this is the right thing to do here.",
      "reference": "Tests are failing because the exception type is NullPointException here if the soupBlob is deleted (so instead of a mal-format json, it's a null)"
    },
    {
      "prediction": "I'm not sure if this is the right one.",
      "reference": "Glad we fixed this as well. Blockly is going to be left as-is for this case, right?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I had accidentally deprecated this class. This is meant to stick around. Only `SalesforceObjectType` goes away."
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's not a string, but it's not a string.",
      "reference": "`hex(i)[2:]` is trying to do the same thing above. what is `i` in your malformed case?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this change is redundant; see the previously defined method \"writeUnescapedXML\"."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Ah now I have at least some idea what these are for."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe in previous PRs @mccheah frequently used `fileSchema` -> `newFileSchema` type of renames to avoid hiding fields in builders. Would it make sense to make it consistent?"
    },
    {
      "prediction": "I think this should be a function that returns ErrConnectionCancelled.",
      "reference": "Do we really need separate error in manager if utils.ErrRequestCancelled is the only error which indicates cancelation ?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Leave as `cpp` since that still gives better results."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "temp change so the predicate can be used by the `exp` package"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Just as a tiny clarification, this isn't affected in any way by \"speak typed characters\". That is, \"caps lock on\", etc. is always spoken, even if speak typed characters is off."
    },
    {
      "prediction": "I think this should be pipelined somehow.",
      "reference": "@dgoodwin Will it cause an issue when the issue get fixed in OLM?"
    },
    {
      "prediction": "I think this is a bug in Nethermind.Blockchain.",
      "reference": "This option is now unnecessary"
    },
    {
      "prediction": "I think this is a bug in the tests.",
      "reference": "Don't jump down to the unexported interface: just set the content type to `\"application/octet-stream\"` explicitly when creating the `Writer`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Instead of counting this here on clear, can we use a second counter for the deleteTerms next to `bytesUsed`? This would be great. It doesn't need to be thread safe IMO"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@daftspunk @bennothommo I wonder if we need to go as deep as detecting what the default varchar length is with a special character to be parsed by the validation trait since we've introduced the config for it."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the right thing to do with the `sendKeys()` method.",
      "reference": "Also update line 2205 below"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `firstTimeEmpySubject` and `firstTimeEmpySubject` and `firstTimeEmpySubject` and `firstTimeEmpySubject` and `firstTimeEmpySubject`.",
      "reference": "Typo, should read `firstTimeEmptySubject`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The more I see this the more I think the transport layer _should_ actually refer to this as `UnaryHandler`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "The `warn` message here seems to indicate that the forced closure of the SSH connection should raise an error; is that getting swallowed up somewhere and not raising?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I wonder if this is a fitting name. Why \"expands user\"? Wouldn't be `user_expanded` or so be more fitting?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I see what you are doing here, but to stay with the `getter/setter` pattern, should we introduce `set isHidden(value)` & `get isHidden()` which them maintains `_isHidden` with in `vNodeCache`. This will avoid what looks like accessing an internal property like `_isHidden` from `axe.utils.isHidden` & keeps things neat."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "nit: for consistency, have this line and the previous formatted similarly"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "As before, shouldn't mention these as being orion options I don't think. Perhaps just enclaveKeyStoreFile etc."
    },
    {
      "prediction": "I think this should be a `catch` statement.",
      "reference": "What's the thinking here? Only logging when the test has not ended yet?"
    },
    {
      "prediction": "I think this is not a logistic operator, but it's not a logistic operator, but it's not a logistic operator.",
      "reference": "@HyukjinKwon @ueshin (cc @itholic @charlesdong1991 ) Not sure if this is the right implementation ..."
    },
    {
      "prediction": "I'm not sure if this is a `mongodb` or `mongodb+srv`? I'm not sure if this is a `mongodb` or `mongodb+srv`?",
      "reference": "Do we want to add any specific error on how the url is malformed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why NOT self->lastLogIdSent_ = self->logIdToSend_"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Shouldn't this be in the above `if` block where we are setting the installedtimestamp to ensure this only happens for already installed (and/or adopted) clusters?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with tabbed_browser.tabopen(background=False) or tabbed_browser.tabopen(background=False)",
      "reference": "This seems like another unrelated change I've done in `master`."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to add the formatter to the config.formatters.first.output.path.",
      "reference": "Would be good to have another context `\"when a duplicate formatter exists for a different output target\"` that shows that it keeps both. As this stands, the specs could pass w/o the `formatter.output == new_formatter.output` check."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Why not just remove? The CUDA one has been around for while. This one has not been part of any release (?)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "nit: `Contentful` is the word used in the GV API, without the uppercase in F"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "It just does the check, maybe we can name it as checkOperations."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We no longer have karma output in the test file so these selectors were now unique and the target didn't need a child selector. Updated to force non-unique nodes"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This moved from a partial to not being in a partial. How about cleaning this view up further by moving it back into a partial?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "add some form of docs in docstring or on :74 for what the effect is"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Couldn't you import `json` from `kinto.core.utils` here too?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Minor: Hmmm...is it worth setting this explicitly for the tests that it affects?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This was added to fix a race condition and you are reverting it here, right?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Could you add some extra text here, so that it reads \"eth_coinbase function is not available, please use --private.api.addr option instead of --chaindata option\", so that it is clear that the function can work, but different options"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "`new_ncr_work_order_path` ? (I've been slowly moving specs over to that way of calling paths)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should flash be included in the patterns too? It currently isn't."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the contract.",
      "reference": "I suspect I will have to keep looking whether Left/Right refers to contract/Implementation while working on the rules code."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `IResource` extension.",
      "reference": "(ignore this. testing a codeflow bug)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "[Nit] can you change the Usage wording to indicate that the flag is used to opt-out of server certificate verification? (e.g. \"disables validation of the Cassandra cluster's server certificate.\")"
    },
    {
      "prediction": "I'm not sure how to import this package?",
      "reference": "Sorry :) Would be really helpful to integrate something like Eclipse Code Formatter, so it will fail if the code style is broken (the same as eslint fails on the frontend) I use IntelliJ IDEA and their vision of imports is a bit different :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this will still fail on systemd"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The convention in most of the codebase is to use `if isinstance(body, bytes):` instead."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think this would be better as: `label = comp.rsplit('.', 1)[-1]`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We have been creating a language-level context interface for each language instead of parameterizing the generate function."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Same thing about context here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "there is a function to get namespace entry from mutable state directly"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The `Transport::Config` objects don't serialize properly. We probably want to just turn them into hashes at this point."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use the \"ddev-ssh-agent\" command.",
      "reference": "Sorry, typo s/unusuable/unusable/"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "If this is needed, should we check that the configured `uri` isn't already equal to the value of the metastore URI configured via `spark.hadoop.hive.metastore.uris` or any of the other ways of setting it. This would be a breaking change for people who have `uri` configured on the SparkSessionCatalog and have it correctly set (which I believe should be everybody as `uri` is currently required if I'm not mistaken)."
    },
    {
      "prediction": "I don't think this is the right thing to do with `content_type` and `content_type.startswith(\"multipart/form-data\")` and `content_type.startswith(\"multipart/form-data\")` and `content_type.startswith(\"multipart/form-data\")` and `content_type.startswith(\"multipart/form-data\")`",
      "reference": "see above - this is only used to select the correct view, we don't need to handle the boundary information here."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "These tests use a self-signed cert so the CA *is* the cert. I considered making a proper chain to use in the tests, but wasn't sure it was necessary to test here, since we test it in the E2E tests anyway."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "We could, maybe, just directly do `excessDomChildren[excessDomChildren.indexOf(dom)] = null;`. Would this improve the size in any way? This will end-up with a property on the `excessDomChildren[\"-1\"]` but maybe we could live with that?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "this looks like it may be something that needs additional refactoring"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: Remove whitespace (and below)"
    },
    {
      "prediction": "I'm not sure if this is a directory. I'm not sure if this is a directory.",
      "reference": "\"Failed opening\" or \"Failed to open\"."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "and -> or"
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function, but it's not a function.",
      "reference": "Add a `yield User.init()` here to wait for all indexes to finish building"
    },
    {
      "prediction": "I don't know why this is needed.",
      "reference": "I don't think this belongs here. If the application can take a local_ip as input, the application should take care of it, not in this common library"
    },
    {
      "prediction": "I'm not sure if this is a custom data object, but it's not a custom data object.",
      "reference": "@DanHarrin please add a `return true` at the bottom of this method, as the docblock indicates a boolean return value."
    },
    {
      "prediction": "I think this is a bug in the lucene index.",
      "reference": "This is used in o.a.l.sandbox.search.BM25FQuery."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't this work as well for Disjoint?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Same here. This was included to quiet the test for the 3D descriptors. As we removed them, this exception handling is no longer required"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why do you need to load a specific data reader in lbann_library?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "why not ValueTask?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I'm nervous about this line, I don't want to go regenerate a bunch of imageset jobs for clusters that are old, already installed, but don't have a CLIImage set (which they wouldn't because they're old) Adding the Installed guard is meant to address this. Otherwise this *should* recreate the imageset job due to the code in this function that deletes the job if it's finished. (but we don't have our images set due to this clause)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is it necessary to change this file? Doesn't `tableMetadata` call `newTableMetadata`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think that I have a better proposal for this test - improve it so that it would know how to read the list of SupportedProtocolVersions and dynamically use these. The motivation here is that I expect to have another network version soon, and this test seems to be a good test case for that."
    },
    {
      "prediction": "I think this should be a list of table identifiers, but it's not a list of table identifiers.",
      "reference": "What is the purpose of this debug message? I'm not sure how it would help."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Is there a corresponding BUILD dependency to prune?"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "The \"good\" and \"bad\" descriptions confused me a bit. Maybe `allowedContentType` and `disallowedContentType`? Not sure if that's better."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It would be better to just change RWD to throw IllegalStateException if you attempt to execute a command after quit (unless it's a second call to quit())"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You may want to have a look at `func checkClusterFormed(t *testing.T, servers ...*Server)` in this file that I created some time ago. It will timeout at 5 seconds, but will return as soon as cluster is ready."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I see a few places where this blob of code is required due to the removal of `errnum` parameter from `flux_respond` -- trading 2 lines of code for 8. The improvement to the function seems like a good idea, but I wonder if we need a convenience macro or function to do it the old way? You went through and made all the changes, was it overall a net win?"
    },
    {
      "prediction": "I'm not sure how to do this with `trackEvent`?",
      "reference": "I know it's not related to your change, but it's a bit odd that this import uses a relative path rather than the ones setup by webpack. Might be nice to change this one in case we refactor those paths in the future; this one wouldn't get caught in any kind of find+replace."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Good catch, and if we don't declare the newSchedule here, will the last schedule be executed in multi goroutine?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `project.TryGetTargetFrameworks()` method.",
      "reference": "`project` should never be null here, unless we have projects that aren't in the solution? Which we shouldn't have  "
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Simple `for` loop instead of `for_each` would help here by making it more readable."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Looks like this falls through, should break."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Let's default manifest lists and manifests to overwrite. These use UUID-based file names and should never conflict."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please rename [speechView] to [speechViewer]."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would use shorter yet still descriptive names, e.g. `KernelPerCpu` and `UserPerCpu`."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "if we are seeking for the content of only one field from metadata, no need to check whether a user could edit record or not"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should this be camelCase to match the above commands? I am not the expert here so maybe Lucas or David can chime in."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is also missing in CreateScopeFromExecuteAsync. Can you add that there too?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I hope that this does not break anything... Probably needs detailed beta tests."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `config.start_time = 42` instead of `config.start_time = 42`",
      "reference": "@JonRowe in what scenario do you see this being manually set?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I think the work \"trigger\" makes more sense than \"check\" because this is taking an action based on status."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "add a configuration , default put public key in Microservice, if the configuration is set, then put in Instance."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "WDYT about the idea above of making these all verbs that correspond to the input spec?"
    },
    {
      "prediction": "I don't know how to use this class, but I don't know how to use it.",
      "reference": "With the introduction of the enum(s) the constants in the store classes should be removed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I would say `!= 5`; A packet with <5 would be malformed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think you missed removing `Stateful` from `push/config.go`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why would you make it internal? if so then at least protected internal"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should check if the response (`d`) contains bar as response, screw the log. :smile:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@Laurae2 good call. This is the only one I found (with `git grep transfered`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't understand how this work, could you explain ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The abbreviation for \"context\" used extensively inside DR is \"cxt\", not \"ctx\", so s/MCTX/MCXT/."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's a string, so it's not a string, so it's a string, so it's a string, so it's a string, so it's not a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "here is `:seconds` missing again"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "initializing to null makes me uncomfortable. let's have a default value"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is the `GET % HTTP/1.1` scenario right?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "No need to use the fully qualified path the BackendAuth facade, just `use BackendAuth` is fine."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Because it's similar for send/open/change/receive types, then probably it can be just common `nano::epoch nano::block::epoch () const` with override for state_block (like nano::block::link (), account (), representative ())"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please give a more descriptive name and add a command to explain what it does."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "we can never get rid of this..."
    },
    {
      "prediction": "I'm not sure why this is a good idea. I'm not sure why this is a good idea.",
      "reference": "what is the effect of changing these buckets in existing data that is available in the monitoring system? if there are any existing dashboards that use previous histogram buckets they are probably going to be wrong ot invalid? also any reason why we chose these specific values?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `sanitize-tchannel` flag.",
      "reference": "This won't work. For the flag to be passed to the plugin, it should be passed as part of the --plugin argument. --plugin \"yarpc --sanitize-tchannel\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@shiyu1994 @StrikerRUS what do you think about this addition to `c_api.cpp`? I think it's a really useful addition to be able to get this type of information from the `Booster`, but I want more opinions since `c_api` is the main public API for the library."
    },
    {
      "prediction": "I think this is an error message.",
      "reference": "rename Round -> requestedRound and DbRound -> dbRound. we don't need to export the fields here, only the error struct."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This expected value should probably be what you literally expect, otherwise there's a chance getClusterRegion is doing something wrong and the test wouldn't catch it because it's being run for both expected and actual."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "TODO: update unit tests to exercise base64-inline path"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this method knows too much - it is kind of a strange side effect I'd prefer if we had separate method for acknowledging that the onboarding was done and should not be shown again"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Do we need to increase the DB version? Also, should probably be a constant, no?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We could utilize the new isZero method in this if-statement, right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should probably have config have a `t` or a `logger.NewTestLogger(t)`, and return the latter"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this not do the same thing as `copy`? I thought that `copy` just did an elementwise assignment, but maybe I was wrong."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Here we are merging the configs from proto annotations and gapic config. But in other places in this PR we are using the new enum to pick one or the other, right? Or is that not the correct way to think about this?"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "not related to this change?"
    },
    {
      "prediction": "I don't think we need to check for `ANDROID_NDK` and `ANDROID_NDK_HOME`.",
      "reference": "Why is this needed?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "This one could be replaced with a `std::max`, no?"
    },
    {
      "prediction": "I don't think this is a bug in Selenium.",
      "reference": "Couldn't you just write this as an if/else or a guard clause like on line 87? Just seems a bit weird doing this conditional assignment for essentially an if/else."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please use strict type comparisons (`===`), not loose type comparisons."
    },
    {
      "prediction": "I don't think this is the case where the blockhash is not null.",
      "reference": "The filter parameters are a bit confusing. I understand that one of them has to be set, but what takes precedence if a from/to is set and the hash as well? Should that fail?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is that necessary?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "yess so much easier to read in order like this!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "question: would this convention automatically and always apply to all classes derived from `LuceneTestCase` including any non-`org.apache` name spaces or would it be possible to opt-out (without an exclusion list) somehow for custom code that might perhaps have chosen a different convention?"
    },
    {
      "prediction": "I think this is the default value for the passcode length.",
      "reference": "Also found this bug, where we were setting the min passcode length to 6, but the min length for a connected app is 4. This can cause problems when the app is force closed or the shared pref is removed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why was this change necessary?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I kind of did this deliberately, so everything from the distributor appears in the same set of logs."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We already have a `seq = pkt[TCP].seq` so you can just re-use it."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We avoid wildcard imports because it isn't clear where symbols are coming from and there is potential for collision. Could you roll back this change? (As well as the additional newline, we don't use breaks in imports either.)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why are these variables renamed? Is there a conflict with some Windows specific variable?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do you test for file existence simply to reduce the warning message that may occur using the include? Also - I think the practice used in BOINC is to go ahead and use include_once even though it isn't strictly necessary in this case."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "`TimeChaos` does not contains a field .spec.action"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You need to override where possible in rs-api"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should this have an add/update/etc pattern? What happens if I need to change some set of data? May be better to just let the callsite manipulate the dictionary."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I don't think this should be added to PyRegion. Adding it here requires that every region have an \"algorithm\" which may not always make sense and the return value type will be different in every case. But fine to use the same name in the regions where we choose to implement it as a convention if that makes the API more discoverable."
    },
    {
      "prediction": "I don't think this is a bug in the upstream.",
      "reference": "Returning here bypasses all the health check and load balancing features."
    },
    {
      "prediction": "The \"License\" is not included in this file.",
      "reference": "Should revert this copyright change, when the file isn't changing in any other way."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Interesting that filepath.Dir(\"thing\") returns \".\" whereas this returns \"\""
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Nice, I did not know about that"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Since the lock is have moved outside of this function, I think it would be simpler and efficient to just return a ref to the std::vector<hsa_executable_t>? That way, we don't need to make a new copy on read and we won't actually need a write operation."
    },
    {
      "prediction": "I think this is a bug in iotextypes.BlockIdentifier.",
      "reference": "also fetch block hash of this height and return hash"
    },
    {
      "prediction": "I think this is a bug in Datadog.Trace.",
      "reference": "Why do we need this in this sample app and not the others?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't need this additional method."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Shouldn't this return code conditionally? The above line seems like an error occurred."
    },
    {
      "prediction": "I don't think this is a valid type?",
      "reference": "What is the need to use string as key? Can we use the apis type as the key?"
    },
    {
      "prediction": "I'm not sure if this is a complex message, but I'm not sure if this is a complex message.",
      "reference": "how about a default parameter instead?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "i don't think we need to add duplicate check for clusterinstallref here, the function already assumes that it was invoked for clusterprovision"
    },
    {
      "prediction": "I think this is not the case where the number of proposal is not 0.",
      "reference": "\\`bbox_feats.shape[0] > 0\\` requires the number of proposal is not 0."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same here. Any way to fit on one line?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "using folly::to is better ?"
    },
    {
      "prediction": "I don't think this is a problem with the `set_profile` method.",
      "reference": "I'm guessing this is unintended?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `this.resumeToken` or `this.startAtOperationTime`?",
      "reference": "This looks a little suspicious to me, can you explain what's going on here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `force_user_id` in the `ENV['FORCE_USER_ID']` variable.",
      "reference": "Can you talk about this? I'm not sure I follow why this is necessary."
    },
    {
      "prediction": "I'm not sure if this is a lightbox layout?",
      "reference": "Is there really a need for this 'simple' layout? Is there a reason you can't use 'lightbox'? The only difference seems to be that the lightbox layout includes Piwik/Google Analytics tracking and simple does not. If tracking needs to be disabled for some reason, perhaps there is a way to do that without creating a whole new layout."
    },
    {
      "prediction": "I think this should be the case where we don't want to merge on the commit.",
      "reference": "Can you say what exception will be thrown in that case (or add an `@throws`, below)?"
    },
    {
      "prediction": "I don't think it's a bug in Python 2.7, but it's a bug in Python 2.5, but it's a bug in Python 2.7, but it's a bug in Python 2.7, but it's a bug in Python 2.7, but it's a bug in Python 2.7.",
      "reference": "Is this meant to be \"2.7\" or \"2.6\". The two lines in this commit don't agree with one another. Looks like everything else in this PR is \"2.6\" and that seems sensible."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should we put these tests in a `generators` directory?"
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "I think that it makes more sense to keep these with the standard definition of non-zero is true and zero is false."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Any idea why you want to change the behavior here? Is there a security risk not to have the prefix in the principal here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this reads like \"mock database cache\", maybe a clearer name"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Nit: move this with the other CM imports."
    },
    {
      "prediction": "I'm not sure why this is the right thing to use.",
      "reference": "This change should be mentioned in the CM"
    },
    {
      "prediction": "I don't think this is the default value for `SpanCreationSettings.Parent` in <see cref=\"Tracer.StartActive(string, SpanCreationSettings)\"/> in <see cref=\"Tracer.StartActive(string, SpanCreationSettings)\"/> in <see cref=\"Tracer.StartActive(string, SpanCreationSettings)\"/> in <see cref=\"Tracer.StartActive(string, SpanCreationSettings)\"/> in <see cref=\"Tracer.Start",
      "reference": "Do we really want a new type, or can we just use `SpanContext`? The `ISpanContext` interface is read-only, but there's nothing stopping users from casting this to `SpanContext` and modifying it."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the license.",
      "reference": "Should we define a const like NETFRAMEWORK or NETFULL which will be set for NET452 NET461 and anything like NET47 etc in future?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "maybe start an issue to capture params that we need final values for and link to it here?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Can we instead do the check in find_instance_group_by_url() ? if we return None when group is not found, it will hit the next if statement (if not instance_group) and continue as expected, in this case we don't need to add 3 separate if statements"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "on my android \".a.m\" and \".p.m\" is used add `||` here to support both variants"
    },
    {
      "prediction": "I don't think this is the case for a multiplane image.",
      "reference": "`!FormatIsMultiplane(image_format)` will always be true at this point due to the test on line 4639."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Maybe inline the CachedAccessor code? Is it similar to our lazy property? If yes, can we reconcile the two?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit this file has unintended changes."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Potential NPE? `hasMedia && selectedItem...`"
    },
    {
      "prediction": "I don't know how to do this with the `volume_type` and `iops`?",
      "reference": "PEP-8/consistency with the rest of the code."
    },
    {
      "prediction": "I don't think this is the case for the `MongoDbClientAssembly` and `MongoDbIntegration`.",
      "reference": "nit: Would you mind moving the `ParameterTypeNames` assignment into each of the method-specific attributes? That could reduce confusion if we later decided to instrument other methods in MongoDb"
    },
    {
      "prediction": "I think this is a hack, but it's a hack, but it's a hack, but it's a hack, but I'm not sure if this is the case.",
      "reference": "Is exposing SpecProvider needed here?"
    },
    {
      "prediction": "I don't think this is a bug in MvvmCross.ViewModels.",
      "reference": "So this will only be executed when it is true. I'm not sure that makes it always usable. Why not make the afterAction, `Action<bool>` and always call it, with the result as parameter."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Tim, please add { } to this 'if'."
    },
    {
      "prediction": "I don't think the default host is used when none is specified.",
      "reference": "Suggest moving to `enable.go` since thats only place used."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This changed when I rebuilt my docker container. Not quite sure why, but might have to do with what my host network configuration looks like when it's rebuilt."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Local cache of what? What's stored in it?"
    },
    {
      "prediction": "I think this should be a string, not a string.",
      "reference": "If the copied `DataFile` returns null, shouldn't the copy also return null? Why not make the builder use `Integer` instead of a primitive here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You could just do this test in the `save_html` function above, and then the users of the save html function don't have to worry about it."
    },
    {
      "prediction": "I think this should be removed in a future release.",
      "reference": "I think I'd prefer not using the formatted string when it comes to unit test, since we don't pass in any string variable as params."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `mimxrt1062` package.",
      "reference": "Maybe it would be better to explicitly include devices instead of explicitly excluding devices?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This could be `for (auto bond: bonds()){`, right?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is $config no longer being used? Can we remove this line?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "can you revert changes to this file."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I don't believe the change is sufficient to correctly handle variable substitutions in the name. As part of the process command we pass the original role object that was retreived without taking into account the substitution. So while the first template apply command will work fine because the original role does not exist thus it's a new add operation, if you try to re-apply the same template again, we'll pick up and process a wrong original name thus we'll try to execute an add operation again instead of modify. So we need to take into account the substituted name when we retrieve the original role as well. Same change should be applied to both policy and service blocks as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please add this to IMvxMainThreadDispatcher as well"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is it possible for opt not to be a string? I couldn't tell if this was a typo or if there is actually a case where it is not a string."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Let's move this up next to the `id` as we usually have `className` as one of the first props."
    },
    {
      "prediction": "The `quilt3` PyPi package allows you to build, push, and pull data packages in Quilt using Python.",
      "reference": "While you're in here, \"build, push and install\"?"
    },
    {
      "prediction": "I think this is a bug in OpenTelemetry.Metrics.",
      "reference": "Unit never made it to spec...so removing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We have RequestStart which seems redundant a bit to this one, WDYT?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think we can remove this corresponding export from `preact` now! Double check no other s using though lol"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'm not sure why this would be in here. Were you working off a branch based off of master? These lines were removed in a previous commit because the table is actually called 'cart_item_traits'."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Maybe `DEFAULT_GITHUB_API_ENDPOINT` would be a better name, since we refer to this as an API endpoint elsewhere?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "If/when you rebase from `dev`, this is going to cause a merge conflict. I'd suggest that soon after merging this PR as the capabilities code has been moved to \"agent/app/agent_capabilities.go\""
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "What is the test case here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You could try moving this closer to the call, where we request label info. We might be doing the check very early.. all the resources may not be present with the informer at this point."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's not a string, but it's not a string.",
      "reference": "Can we add these up by the data files counts?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Most of the time assigning won't save bytes unless used 3+ times (var adds 3bytes)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I would rather find the code that inverts the logic and remove that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The else doesn't return anything?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "assignments should only be cuddled with other assignments (from `wsl`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why not simply `paths = search_path_opts.LibrarySearchPaths` ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Are we sure this should be translated by the web client? It was unclear in chat exactly what's getting translated here."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "same oneof issue."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `resolve_references` method.",
      "reference": "If we resolve here, isn't the whole `module_install` config setting or any subkeys also pluggable? I think that's totally fine, just want to make sure that that's known, and we should also update the data in `options.rb` for those options"
    },
    {
      "prediction": "I don't think this is a bug in ihipExtLaunchMultiKernelMultiDevice.",
      "reference": "it would be better to change `kds` into a `std::vector` then we don't need to explicitly free it"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Looks like you're also changing logic and not only tests."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is it possible that test failures here are real and that we should improve the rate limiting logic? Or are we ok with rate limits to be exceeded by 15%?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Shouldn't there be some kind of validation somewhere? IMO there should be an exception if `$options['lazy']` is not a boolean."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: please move it inside namespace."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "The inventory schema needs to be regenerated to include these options. Looks like the CI job didn't get triggered since the paths don't include `lib/bolt/transport/**`.  "
    },
    {
      "prediction": "I'm not sure if you want to use the CapsLock as the NVDA key.\\n\"",
      "reference": "This might break if a user runs the system tests with a system language other than English, in which the user default language differs."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was raising intermittent errors, since Lorem ipsum contains the word \"error\""
    },
    {
      "prediction": "I think this is a bug in RTPSDomain.removeRTPSParticipant.",
      "reference": "Shouldn't we then add `mp_impl = nullptr` to the destructor of `RTPSParticipant`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Are the additional brackets necessary?"
    },
    {
      "prediction": "I think this is not a problem?",
      "reference": "consumerMeta only belongs to this invoker instance only relate to this one consumerIntf class seems no need to build a complex key?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "this one is unrelated right? (Don't mind including it, just making sure I understand)"
    },
    {
      "prediction": "I don't think we want to use `grad_clip` here, but we want to use `grad_clip` instead of `grad_clip` instead of `grad_clip` instead of `grad_clip` instead of `grad_clip` instead of `grad_clip` instead of `grad_clip` instead of `grad_clip` instead of `grad_clip` instead of `grad_clip` instead of `grad_clip`",
      "reference": "8, 11 actually achieves similar performance, we should use our default config if [9,11] is unnecessary."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "For a separate PR: Can we make this a JSON/Thrift procedure instead? It could accept the amount of time it needs to sleep as an argument."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure if this is the case.",
      "reference": "Please remove this blank line."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "the cartTrait is not used anymore"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Cn you please make the message more human friendly."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `qutebrowser.utils` module.",
      "reference": "Please do `import enum` instead, then use `enum.Enum` and `enum.unique` - we do this everywhere to see where things are coming from, except for Qt (everything begins with a `Q` anyways) and typing (mostly used in type annotations, so it's clear without the namespacing)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Isn't ENCFAIL used in codec.c below? Wouldn't this make it no longer compile?"
    },
    {
      "prediction": "I'm not sure if this is a static class.",
      "reference": "this looks very weird"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "So, the culprit was actually this class \"ConsoleLogHandler\", correct? Because it simply wrote to stdout..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Still curious why you need to modify this method? Why not in the future just have a method called `LogFactory.ReloadConfiguration()` instead of the config assigning itself?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should this say \"lint, cleanup, destroy, dependency, syntax, create, prepare, converge, idempotence, side_effect, verify, cleanup, destroy\"?"
    },
    {
      "prediction": "I think this is a bug in p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p/p2p.",
      "reference": "I am not sure why these log messages are changed."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `reflect` or `unsafe`?",
      "reference": "This panic is incorrect - this is a full implementation of a slice equality check. This should be something more like `type x is not comparable` maybe?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the extra_opts array?",
      "reference": "See below: let's use the existing convention _tcsnlen."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why don't we need this any more?"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but it's a hack, but it's a hack, but it's a hack, but it's a hack.",
      "reference": "clean unnecessary comma"
    },
    {
      "prediction": "I don't think it's a `null` here, but I don't think it's a `undefined` here.",
      "reference": "This is the default value for enumerable."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Just above, you have `const auto` for a `RDKit::MOL_SPTR_VECT::const_iterator`, here it is only `auto`. Why is this?"
    },
    {
      "prediction": "I think this is a bug in pugi.js.",
      "reference": "@djarek just a quick question, wouldn't be `ptr.reset()` here better as it does not memory leak if we do not call delete on the raw pointer aswell? it maybe makes sense to use `ptr.release` if the event is guaranteed to be loaded again but on a reload it would memory leak if for example I removed that script from my files before reloading or not?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why to `Get()` value twice, while u have it 2 lines before"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `registerConsoleCommand`?",
      "reference": "There is a typo here, this needs to state `october.fresh`"
    },
    {
      "prediction": "I think this should be the same as `createDummyTable(File tableDir, File dataDir)`",
      "reference": "Metadata tables loaded through `HadoopTables` will have their names as location.type (which is weird as we normally use location#type). I am not sure whether it is a big deal or not."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you explain why you went from a positive value (metrics.viewTop) to a negative value?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `withLockedTasks` and `withUnlockedTasks` parameters.",
      "reference": "Let's use a dedicated DTO instead of `List<String>` to remain consistent with all other existing REST API endpoints: * Introduce a new DTO class (e. g. `ExternalTaskTopicNameDto`) located under `org.camunda.bpm.engine.rest.dto.externaltask` * The class should have the attribute `topicName` of type `String` * Introduce a getter & setter for the attribute * Convert the list of strings to a list of `ExternalTaskTopicNameDto`s * Change the method signature to return `List<ExternalTaskTopicNameDto>`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you plan to remove the `ScriptDTO getScript(List<String> path);` method long-term?"
    },
    {
      "prediction": "I'm not sure if this.allTypes.length is the same as this.allTypes.filter(function(item) { return self.allTypes.some(function(enabledItem) { return self.enabledTypes.some(function(enabledItem) { return self.enabledTypes.some(function(enabledItem) { return self.enabledTypes.some(function(enabledItem) { return self.enabledTypes.some(function(enabledItem) { return",
      "reference": "@itsiprikshit I used a custom v-model to app count component because the sourceapps component was not reacting to user app count selection, e.g. whenever user changed app count selection, the source apps selection multiplicity remained the same. As a matter of fact, user was able to select one application only. Please let me know if you have any thoughts on this."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Similarly, we think we may keep `fused_semantic_head.py` unchanged. Then, we could add a new mask head for the desired function."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why implement this? It duplicates the value in FeatureConfig."
    },
    {
      "prediction": "I'm not sure if this is a spark streaming microbatch scan.",
      "reference": "@aokolnychyi / @RussellSpitzer / @holdenk Spark3 gives ScanBuilder - abstraction - to define all types of Scans (Batch, MicroBatch & Continuous). But, the current implementation / class modelling - has SparkBatchScan as the Scan implementation. Looking at some of the concerns of BatchScan - all the way from the State maintenance of a single SnapshotId to read from, the asOfTimeStamp & features like VectorizedReads - all of these don't seem relevant to Streaming Scans. So, I feel that we need to divide out Streaming Scans into a different class. Does this thought process - make sense? If we go by this route - do you folks know - how to pass different Scan objects to Spark based on Batch vs Streaming?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Will you please update these files to use a copyright end date of 2021?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Adding fixture to the body as we don't have the `runner.tmpl` anymore"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "nit: just for consistency we can move this import block down. Right above openshift/hive imports"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Perhaps clean up the commit history and don't squash?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just `writeBytes(content.array())` Back to my original, somewhat broken version ;)"
    },
    {
      "prediction": "I don't think this is a problem with the `ctxpropagation` name.",
      "reference": "I couldn't tell from reading the test - do we every criss-cross transports in the same test? I want to make sure we aren't breaking the chain..."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "File is not `goimports`-ed"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "do we want to still validate that the context had a nonzero TTL? i suppose it's fine to let clients determine whether or not their streams will timeout (though we still don't have the means to cancel them from the server other than EOF), and they can still cancel their own contexts - so maybe not a huge deal, but thought it was worth bringing up."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Go ahead and provide the same implementation for all of the languages - I'm not sure there's a reason for it to be different."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should also test type confusion here (e.g. `{\"anticache\": \"foo\"}`)"
    },
    {
      "prediction": "I'm not sure if `dartfmt` fails, but `dartfmt` fails.",
      "reference": "I'd love to trim the content of `unformatted` too. Any ideas?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "can you remove this unrelated change?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Would using `HintLabel` here instead (without `setObjectName`) work?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "From what I can tell, the `serviceAccountFile` is never set to anything except \"\"? It'd be best to remove this altogether, so we don't mislead future developers  "
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Why do we remove the Sign in link?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `move_to_top_item` and `move_to_bottom_item` and `move_to_bottom_item` and `move_to_top_item` and `move_to_bottom_item` are the same as `move_to_top_item` and `move_to_bottom_item` and `move_to_bottom_item` and `move_to_bottom`",
      "reference": "holy crap, were we really missing a 'break' statement here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This doesn't seem to be used anywhere, probably doesn't need to be a new interface."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is a good start, but what do you think about just using `libkbfs.GetCurrentSessionIfPossible()` to avoid calling this altogether if there's no session? That way we can avoid continuous RTTs to the server when logged out."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "This `aria-labelledby` stuff is all new to me, but my reading of the spec is that the value should be a list of element id values, and `dLabel` doesn't seem to be the id of any element?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Does this fail validation if you now use the `upload` key instead of `source`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we use GetCliGlobals(false)->exCollHeap() here instead"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I suggest you move the waitUntilAllElected into init::KV() method."
    },
    {
      "prediction": "This is the default value for the `DefaultScheduledDelayMilliseconds` and `DefaultTimeoutMilliseconds` values.",
      "reference": "no need of pub;lic."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Do you think we can name this variable in a less ...negative.. language ? maybe `ProposalTieBreakerEqualizer`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you add back these newlines? We try to avoid non-functional changes like this because they can cause commit conflicts."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `newState.searches` array.",
      "reference": "Why not just `if (!searches.includes(action.search)) searches.push(action.search)`? That way you don't need to remove then add the element."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "@demiankatz I'm not sure that this is very useful. I just did it to get started. If we had a small handful of predetermined prefixes that were randomly chosen, it would be easier to distinguish them from the rest of the call number. Would that be preferable?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this deleted too?"
    },
    {
      "prediction": "I don't think this is a class, but it's not a class.",
      "reference": "Given that IApiResponse is already made disposable, this is not necessary."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "client.getSelectedSpellName() can be used for this"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Please alpha sort these filenames."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "is this already called by actPool.validate()?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It is relatively cheap to tell whether a bond is a ring bond, we don't have to perform an SSSR."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Maybe we should add flag aliases for service as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This LGTM but don't we need a winning PoSts field to fully implement the protocol? No need to add here as I'm working on this in another PR, but curious how we can interop with lotus blocks without post proofs."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "can you move the [] into pubSub? so Blockchain just contains a pubSub, not []"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I don't think 100 is a safe default here, since later we check that the value is between 50-95."
    },
    {
      "prediction": "I don't think this is a bug in NLog.Layouts.",
      "reference": "I would be nice if we could describe this without the word \"agnostic\""
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Pick more specific exception types for these cases. Not sure what would be best for this one (`ValueError`?) but the next one could be `IndexError`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This seemed like the easiest solution We need to include this path in `testMatch` to run the test AFAIK *BUT* we don't want this test ran when running them all normally I'm sure there are other ways to do this!"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Most of the following test changes can be avoided if need be."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Eventually we might want to move this back as generating this data structure takes some time (for large datasets) and we don't want it in the hot-path of `osrm-customize` runs. Thinking long-term making `osrm-customize` eventually digest `.osrm.cells` will will enable only updating cells selectively and using an earlier customization for the rest."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "You're not really using named result variable - you can just leave `error`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It wasn't possible to call this method with `PartitionSpec.unpartitioned()` as the schema in the spec was empty."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this namespace is never used"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Well, if you call `Nack`, it _will_ be redelivered. So maybe reword."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `wistia_video_embed` method.",
      "reference": "Why did we make this a static string?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please re-run PYTHONPATH=. python tests/services/inventory/update_cai_dumps.py following the instructions at the top of this file to ensure the test files have the correct CAI asset type."
    },
    {
      "prediction": "I think this is a problem?",
      "reference": "`stateDB := NewStateDBAdapter(sm, 0, hash.ZeroHash256, NotFixTopicCopyBugOption())`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the number of spots.",
      "reference": "There are unneeded parens here, but I'll fix it up when merging."
    },
    {
      "prediction": "H2O does not support `h2o_mruby_eval_expr` in the `h2o_mruby_eval_expr`?",
      "reference": "Just one more thing... How about doing all of the following? 1. renaming h2o.rb to bootstrap.rb 2. require and include the acl code _from_ bootstrap.rb"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Commit message: \"remove\" is misspelled."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is a pretty idiosyncratic method - I'd move it into the JSON-RPC package rather than adding it to `BytesValue`."
    },
    {
      "prediction": "I think this is a bug in RSpec.config.apply_derived_metadata_to(@metadata)",
      "reference": "Is there a way to deduplicate this somehow? Could we roll it into `RSpec.configuration` with a bit of memoization or is there a chicken and egg problem."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Generally, I wouldn't say I like the idea of providing properties that return negative/inverted values. It would be more convenient to return whether the update is **in** progress or not."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Converting playbackManager to operate in ms (preferred solution, imo) would allow us to completely drop this function."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The default value should be a bigger one, I'd like it is the maximum of int32. That means we will not cut-off anything by default. And users would config it with an appropriate value in config-file, such as 1000 or 5000, etc."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Probably missing return here as well"
    },
    {
      "prediction": "This is a hack.",
      "reference": "On second thought... this affects how often the function specified by the `load` property is run. So I wonder if, for consistency, we should call this `LoadInterval` instead. Does that make sense?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `require('../../../api/lib/countly.common.js')` instead of `require('../../../api/lib/countly.common.js')` instead of `require('../../../api/lib/countly.common.js`)`.",
      "reference": "Now you don't need the localization module here then :)"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This should not convert each value to a literal on every invocation. Instead, this PR can add a `literals` method to `BoundSetPredicate` to access the values as literals. That way, the conversion happens once and can be lazy."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think we still need this exception if doesn't have LIGHTGBM_BUILD_DOC"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this make it easier to read? Previously this would have run `kubectl describe certificate` right? In which case it would have included events related to the cert. Will we miss that? Would the old `kubectl describe` output have gone to stderr?"
    },
    {
      "prediction": "I don't think it's a string, but it's a string, but it's not a string, but it's a string, but it's not a string, but it's a string.",
      "reference": "Just an understanding question: do we need a map here, would a list/set of Strings be sufficient? we are not adding entries with `false` here, are we? Being in the list already means it's used, right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Ah, so the change is that you want the `prune()` side effect before doing the `task.id not in necessary_tasks` membership check? Stupid non-Haskell programming languages :p"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This change was not really intended but made by the linter of VS Code. And looking at other packages this looks like a best practise to place interal packages on the top and gh imports afterwards."
    },
    {
      "prediction": "I think this should be a `readPreference` property?",
      "reference": "Do we normally force ReadPreference primary on other write operations? Or is it just that we normally ignore it?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Instead of returning null here and discarding nulls automatically, I think this should return null (or some other signaling value) and fix the part that consumes the output of the visitor."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Really, we want to be setting the validatorsForPreviousBlock against the yet to be created block, so it might make sense to update the cache once the block is created/imported instead."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It seems to me that the original implementation was correct. Can you share what the scanner was pointing out?"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but it's not a hack, but it's not a hack.",
      "reference": "Instead of doing that, please create an `assets/js/googlesitekit-subscribe-with-google-bulk-edit.js` file as entry point - all our entry points should be located in `assets/js`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This is not valid, a `div` shouldn't be in a `span`. You could apply the `className` attribute to the `span` tag."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would it be possible to reuse RcJobExpireDuration and RcJobExpireInterval and auto delete them when job is deleted?"
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "Python wants **future** imports to come first."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Better to call this before EXITING_DR which is supposed to be last."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Does this work at runtime?"
    },
    {
      "prediction": "I don't think this is the default value for `maxRetriesOnRecoverableFailures` and `maxRetriesOnRecoverableFailures`",
      "reference": "Hmm why do we need to make this change? Like which one requires this change?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `require`?",
      "reference": "why remove this and other piece?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Yikes... That was probably me."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "It would be better to move the ... outside of the l8n block. This way it won't need to be translated for each language twice."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "That's a huge load of new dependencies. I think it's better to create a reload function on ScriptManager and control with enum instead."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`NewUpgradeTaskJob` -> `NewUpgradeResource`"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Is that the memory usage of the system or the process / awesome?"
    },
    {
      "prediction": "The `callback` is not a function.",
      "reference": "\"change\" *and* \"schema\" events (A bunch of these; not marking them all)."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I think there is probably a shorter, more descriptive name for this. Something like `commitAtSequenceNumber`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The `url_name` should definitely be more than just 1 character long at the shortest. How about 3 or 4 characters?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `TypoScriptFrontendController` class.",
      "reference": "Please revert this change"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nice. I hadn't even heard of presenters in Rails before (learn something new every day) :)"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "`string[]` ? not sure, can you verify this @core23 ? Thank you"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `shell.disableFullscreen`?",
      "reference": "are we aware that this breaks older browsers like WebOS? :) they don't handle `let`"
    },
    {
      "prediction": "I don't think this is the right thing to update the TTL value in the record.",
      "reference": "This isn't really a Kinto record but a Memcached record. I could kind of go either way on this."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Kick off the download after login."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I don't think you need to change this, `array<int, string>` should be accepted whenever `string[]` is expected. (`string[]` is an alias of `array<string>` itself an alias of `array<array-key, string>` which is a parent type of `array<int, string>`"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "TODO: fix this, probably in another PR"
    },
    {
      "prediction": "I don't think this is the case for the tabbed-browser, but it's not the case for the tabbed-browser, but it's not the case for the tabbed-browser, but it's not the case for the tabbed-browser.",
      "reference": "Is there any case that tab is None?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "pls use `err` instead of `e`"
    },
    {
      "prediction": "I don't think we need to check for the gamepads in the browser.",
      "reference": "`attachGamepadScript` above can also be placed inside."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "when we use RegisterWriteCommand,this func should be exported,so we can use this to get signer at the outside action package"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Dead code - we should remove it or use `log.Trace` for lower logging level. Same applies for change at line 138."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "How does this make sure invalid coordinates making the parser fail? Relying on the Coordinate type's boost numeric_cast calls in the ctor? Shouldn't we rely on a coordinate's `.IsValid()` member function instead?"
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "Simple Storage **Service**"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Does this line (and the corresponding one in the test bootstrap) actually do anything? I don't see where CACHE_ENABLED is used as a global constant."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "has this changed? are we testing \"all possible situations\" now?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "ZK is properly spelled 'ZooKeeper' (capital 'K')."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Guessing this locates the key you get when you run `gcloud auth application-default login`? What was the previous behavior/the behavior for the manual Veneer creds?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "looks good to me, but it would be better if you assigned `this.countRows()` into a variable, so it doesn't trigger twice in the return statement"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "For now, don't add \"use strict\" to any existing files. That's a separate project that we'll do later. (New files can use \"use strict\".)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I was confused by this env name variable, assuming it was the value, not the name. Silly nit, but maybe name it noninteractiveEnv?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "`sys.platform` could be equal to `darwin` which is posix. Use `not startswith('win')`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "let's move this into `slack_helper.go`"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I doubt it will work, but without space between -o and ControlPath it should. Lets see. What I do not understand is why we did not see a failure on CI related to this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is the reason we might be seeing 360 as discrete bearing"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`FULL_VERSION` is available at module level for others to use, but it won't have `%(prog)s` substituted with pylint. Will that be a problem. Also put it here instead of __pkginfo__ with other versions because it isn't pkginfo related."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Is this needed? I don't see any uses."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Shouldn't this be V1beta1?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I think there's an `approval_for`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Here we should use <code>List</code> in generic"
    },
    {
      "prediction": "I'm not sure if this is a no-op, but I'm not sure if this is a no-op. I'm not sure if this is a no-op. I'm not sure if this is a no-op. I'm not sure if this is a no-op. I'm not sure if this is a no-op. I'm not sure if this is a no-op. I'm not sure if this is a no-op. I",
      "reference": "The `JavaCompile#getToolChain` method got removed and I am not sure what a good replacement is. I replaced it with `targetCompat` for now but they are not equivalent. Maybe we can use `JavaVersion#current` here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The method name is incorrect. It does not check the existence of the file. I'd suggest deprecating both methods `fileExists` and `findIdByHash` and use findIdByFilename instead of fileExits"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "We have `stdbool` imported, might as well use that for clarity."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "File is empty, consider removing?"
    },
    {
      "prediction": "I think this should be the same as `batch.execute(self.configuration.writeConcernMax().writeConcern, function(err, result) { expect(err).to.exist; expect(result).to.not.exist; expect(result).to.not.exist; expect(result).to.not.exist; expect(result).to.not.exist; expect(result).to.not.exist; expect(result).to.not.exist;",
      "reference": "`writeConcernMax` was changed to return a `writeConcern` formatted the new way-- `writeConcern: {w:1, ...}`. Bulk execute takes an actual `WriteConcern` object as its first parameter (this was changed in master), so we have to un-wrap the `writeConcernMax` result here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "How about passing this through the `config`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Out of curiosity - did we make this change to allow dynamically assigning a value to `os.environ[\"TEST_TARGET\"]` during test execution? I kind of liked the decorator style `@only_localstack` - makes the condition a bit more explicit. Looks like `skipif` also allows to specify a condition string, e.g. `pytest.mark.skipif('os.environ.get(\"TEST_TARGET\") == \"AWS_CLOUD\"')` - could that be an option? (not sure if that gets lazily evaluated at runtime right before the execution of the annotated test method starts, though..)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with it.",
      "reference": "I noticed (SonarCloud noticed actually) that the implementation of `::edit` method is the same as `__construct` is. Does it make sense to call the `edit` method from the constructor?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "would you please rename the message prefix to: [in_syslog] ...\""
    },
    {
      "prediction": "I think this is a hack, but I think it's not a good idea to do this.",
      "reference": "The pointer to a pointer is kind of gross. How about either taking the `ROMOL_SPTR` directly or, preferably, returning an `std::pair`?"
    },
    {
      "prediction": "I think this should be a function that returns the number of pending transactions in the pool.",
      "reference": "the name confusing, please rename to `pendingCountNoLock` or similar"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "line is 175 characters"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `restClient` parameter.",
      "reference": "@ivanbogdanov Does this fix the first time load gray screen issue that @wmathurin noticed?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `pip install lightgbm` command.",
      "reference": "Is `2.3.0` version OK?"
    },
    {
      "prediction": "I don't think this should be the case.",
      "reference": "I tested it only in Firefox (`./go //rb:firefox-test`)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "separate third party and builtin"
    },
    {
      "prediction": "I think this is the case where we need to finish the front activity.",
      "reference": "@smcnulty-sfdc We do want to finish the hybrid activity in our hybrid apps though. Could the caller not pass in `frontActivity` instead? Or start it up again post-logout?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "isn't this going to return a timeout error if the context is canceled?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`argNameVal.length` will still be !=2, so line 22 will give true and then continue on line 24"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It was `$chars[$i]` I believe."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This has the likely potential to break existing tests that are relying on the old beaker behavior. If we are going to release this in beaker 3.x, then we need to preserve the old behavior as well (so set both the `upcase` and original values). On Windows, they env variables will overwrite each other, with the same value, so not an issue. On *nix, there will be two env variables, but they will have the same value, so again no issue."
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the right thing to do with the user.",
      "reference": "Thanks for fixing this! I probably didn't test the playground when making changes here for cloud variables."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I will also check if `nameMapping` needs a precondition null check."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Since RuntimeIOException is deprecated and you are touching this code, why not replace it?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "You should also have a test that calls it with tm_cpp and make sure it returns the correct JSON file."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "One more minor change, the string `ForAdditionalLiveTvOptions` is probably also unused."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "How to distinguish between warning and error?"
    },
    {
      "prediction": "I don't think this is a problem with the UIAHandler.",
      "reference": "Perhaps you want to check if UIAHandler.handler is not None. The current check will break NVDA if you call UIAHandler.terminate() for some reason."
    },
    {
      "prediction": "I'm not sure if this is a `BaseReplacePartitions` class, but I'm not sure if this is a `BaseReplacePartitions` class, but I'm not sure if this is a `BaseReplacePartitions` class.",
      "reference": "can we make `replace-partitions` property a static variable in `SnaphotSummary.java`?"
    },
    {
      "prediction": "I think this is a bug in Selenium.",
      "reference": "Maybe call it `WireBridge`?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Should really be `one()`, not `one_or_none()`"
    },
    {
      "prediction": "I don't think we need to set the node-labels in the kubelet extra args.",
      "reference": "Should we use strings.Split and strings.Join instead of manual concatenation?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `_asset_partitions_fn`?",
      "reference": "rough that this needs to exist, but it is what it is"
    },
    {
      "prediction": "I think this should be a test for the `val` attribute.",
      "reference": "FYI, I pulled your branch and hacked a little on your test case. This passes for me (you may want to tweak further): <pre> it('should not set empty string for null props in custom elements', () => { customElements.define('x-bar', class extends HTMLElement { val; }); // @ts-ignore render(&lt;x-bar val={null} /&gt;, scratch); expect(scratch.childNodes).to.have.length(1); expect(scratch.firstChild).to.have.property('nodeName', 'X-BAR'); expect(scratch.firstChild.attributes.length).to.equal(0); expect(scratch.firstChild.val).to.equal(null); }); </pre>"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "It is the maximum value that the configured emulator can support."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Here, I've been giving priority to the session saved by the user. This means, that if the user quits with `:wq`, then restarts `qutebrowser`, and then `qutebrowser` crashes for some reason, next time `qutebrowser` is restarted, the session saved lastly with `wq` will be restored, and not the one autosaved. What do you think?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "this line got me confused for few seconds, as the `AccountData` is both the name of the data structure as well as the function name. I think that `GetAccountData` is a better choice for a name. ( note that the same applies for the previous `BalanceRecord` function name )"
    },
    {
      "prediction": "I'm not sure why this should be done here?",
      "reference": "I think this mutex is only used here. Remove it."
    },
    {
      "prediction": "I don't think this is a problem with the migration.IsDBVersionEnabled() method?",
      "reference": "so this is now init to 1?"
    },
    {
      "prediction": "I don't think the version is the same as the version of the spawngroup.",
      "reference": "For future note; not prefixing the table in a join can throw an error in the query parser depending on how the query is built I am making an assumption this was tested"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `time.Second * 10` for now.",
      "reference": "Had to bring this up, will abandon this style of testing based on Joel's work soon."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What does our source validation complain about here? Many of the logok/nowarn places look fine to me at a glance but I'm no match for the logging policeman ;-)"
    },
    {
      "prediction": "I don't think this is the right thing to do with `stats.SessionStats`?",
      "reference": "It feels like this dependency should not be here. Some deep internal openvpn package (middleware) knows about one of possible stats consumers. Maybe as an alternative, statistics and state callbacks can be extracted as separate interfaces in top openvpn package and reused by both sides"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Can you please remove `codec` from the parameters too? I think it's unused now."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "mocks needed this change so that it returns the \"right\" thing"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `configuringShiftClick` and `configuringControlModifier` and `configuringControlModifier` properties.",
      "reference": "I don't think the getters for this are needed, but looks good other than that"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `<%= video.clip.wistia_id %>` and `<%= video.length_in_minutes %> minutes` is the same as `<%= video.length_in_minutes %> minutes`",
      "reference": ":+1: to inlining this."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Does psalm support the same logic internally for object-like arrays? Just want to be certain I can indicate this is a contextual return item `crypto?:mixed`."
    },
    {
      "prediction": "I think this is a bug in VkImageCreateInfo.",
      "reference": "I can't recall if there was a fix specific to this in the past?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `gcpCredsSecret` and `secret` fields.",
      "reference": "Not sure what the todo is here? Is it to support some kind of defaulting based off of that?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure about this name. I think \"explicit\" is also a bit difficult here (I think it should be implicit then) Proposal: FlushOnEvents. Or, It would be cool if we could split into 2 options, FlushOnShutdown and FlushOnReload, but I expect that's far more difficult to implement?"
    },
    {
      "prediction": "I think this is a bug in QtWebEngine, but it's a bug in QtWebEngine.",
      "reference": "I don't think that works - you can't mark a fixture."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `puppetlabs/etc/bolt/bolt.yaml`?",
      "reference": "We should not include this path."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Add newline at end of file"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This should be done when updating to the next release (2.5). You currently only perform the upgrade when users go from 1.4 to 1.5, so it will lead to crashes for existing users."
    },
    {
      "prediction": "Hive feature gates are enabled by default.",
      "reference": "suggest hive.openshift.io/cluster-machine-management or something to make it more obvious what it is."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "We explicitly don't want to do that. This was a complaint from users before."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Hello, The PHPDoc is `string[]` not `int[]`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same issues with parameters order in `ipset_server.go`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `SystemNamespaceRetentionDays` and `SystemNamespaceRetention` config.",
      "reference": "Wow, did it literally mean the retention days is a huge number?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "you probably didn't intend to touch those files in `scripts/`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Similar to `collate_fn`, we may rename it to `tpfp_fn`."
    },
    {
      "prediction": "I'm not sure if this is a top overlay.",
      "reference": "Awesome! We may also use negative rule `never` to fix new lines after `return`: `{ blankLine: \"never\", prev: \"return\", next: \"*\" }`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why can't this be a function on the `Config` interface like all the others?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If the feed is null, the menu items should still be setup. Just the feed title can be left out. That prevents possible flickering when menu items are displayed/hidden for some feeds."
    },
    {
      "prediction": "I think this is a bug in Spark3, but it's a bug in Spark3. This is a bug in Spark3.",
      "reference": "I'm not sure that this should call `allowIncompatibleChanges()` because adding a required column when there are no existing values will break reading the new column in any table with data in it. The only time it is safe to add a required column is if there is no data in the table. What about throwing an exception here instead? I agree that the column should not be optional if NOT NULL was specified. Another alternative is to check whether the table has data and allow the incompatible change if it doesn't have any rows."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Early translation , should be logic-less"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I don't understand why these functions return a request/response, respectively. In all implementations we actually _modify_ the request/response given as a parameter. Do you envisage situations where we'd want to construct completely fresh request/response objects? Even if we do, it's not something needed atm, so I'd favour in keeping the API minimal. Also, the fact that these functions _may_ mutate the request/response should be noted."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Wasn't there a subsequent reason why we had to keep the `/p/project_graph` route? Outside references or is the proposed solution to the original proposal we us `/p/g` as the `compares#project_graph` route?"
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Any suggestions on how I would even _approach_ writing tests for arbitrary values...."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `editThemeCache` property.",
      "reference": "Scope declarations for class constants was not added until 7.1, this will not be accepted."
    },
    {
      "prediction": "I think this is a bug in TThreadedServer::onClientDisconnected.",
      "reference": "The assertion here is that find should never return end() because this is the only mechanism that reaps items from the activeClientMap. If it == end something went horribly wrong."
    },
    {
      "prediction": "I don't think this is the case where the key is missing.",
      "reference": "The `unless the collection ...` part reads a little bit hard, maybe separate into its own sentence and explain what it means by `cannot generate a fresh key`?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Doesn't `gcerr_string.go` need to be updated for this?"
    },
    {
      "prediction": "I think this is a bug in the compiler.",
      "reference": "Both cases allowed by the Go spec are now supported, so it's a bug in the compiler if we get here. You can replace the `todo:` error with a panic. (Note: getting here would be a bug because when we get to SSA level the code has long been type checked and has already been verified as being valid Go)."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `history_prepared`?",
      "reference": "You can simply do `if tab.history_prepared:` here as empty lists are falsey."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "Remove this whitespace"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`show_img` is not normalized while `one_img` is normalized. And line 139 pass `show_img` for pytorch2onnx function. Is this expected behavior?"
    },
    {
      "prediction": "I'm not sure if this is a string, but it's not a number.",
      "reference": "Why is this bounded between -30 and 30?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think even you can exclude to run it on nvcc"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "G104: Errors unhandled. (from `gosec`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "will `failure` always include `arn` and `reason` in its dictionary? If so, :+1:"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with_events?",
      "reference": "Should this be optional, or default to 'action' as well?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "how about formating this import?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Comma police. :) Also, the docstring needs updating."
    },
    {
      "prediction": "I think this should be a struct, but it's not a struct?",
      "reference": "Implement an in-memory implementation of this in the fake driver."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `watchable` option.",
      "reference": "Same question as the other view spec regarding not actually saving records."
    },
    {
      "prediction": "I think this is a bug in NLog.",
      "reference": "Rethrow for `MustBeRethrown()`-exceptions?"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "May clean the unnecessary modification."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `--with-flux-security` option.",
      "reference": "Should this line set the value to `x` since that is checked below?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I don't particularly love the terminology here. Why not simply add `copy(boolean stats)` or a copy with an enum to indicate what portions of the datafile to include? At some point we may want just some of the values (e.g. CBO may want counts, but not lower/upper bounds). Just a thought."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "you could probably remove keyValue and just compare idx vs ann.length (ex I think the goal here is to ensure it works with a value like `foo=`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the file_type?",
      "reference": "we do this to differentiate between the multiple cc files for when the recording is stopped / restarted multiple times within a single meeting"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "You've deleted this code but not added it anywhere else. Should this be used as my proposed example in the .ini file? Do we need a mechanism for configuring a global fallback string independent of the numeric codes?"
    },
    {
      "prediction": "I'm not sure if this is a bug in the future, I'm not sure if this is a bug in the future.",
      "reference": "nit: strip away those imports? seems not used in the new code."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "redundant whitespace :octocat:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't believe that the `assertDictEqual` call can pass without `api_response` being a `dict`, so this second check isn't needed!"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Fuzzer did not like this change. Looks like I misunderstood how the pool works... if allocated from a pool we should never free it manually, right? I think I'll need to drop this patch."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Wouldn't it make sense to already have title, owner etc in this class?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "New generators should have version `next`"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Wrap these two lines inside an `if (node.isMetricsEnabled() || metricsConfiguration.isPushEnabled()) { ... }`"
    },
    {
      "prediction": "I think this is a problem?",
      "reference": "if end_level == -1 or end_level == (self.num_ins - 1): for end_level is the Index of the end input backbone level."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "No CLR overhead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Consider faking the TestClient's GetProject/GetZone/GetMachine methods."
    },
    {
      "prediction": "I don't think this is a problem with the peer chooser.",
      "reference": "Returning a private type as part of the public API? Isn't this impossible for users to implement?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "prefer common_properties::_canonicalRankingNumber if possible, should be quicker in general."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The meaning of `loss_normalizer` and `loss_normalizer_momentum` should be reflected in docstring."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Call to `cloexec_pipe` (or an equivalent function) is missing. I presume that this is the reason why you are seeing timeout errors."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "There are no changes in this file. Please reset."
    },
    {
      "prediction": "I don't think the mean is the same as the standard deviation.",
      "reference": "Should we rename this to tailProbability?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Add the issue number too i#4400"
    },
    {
      "prediction": "I think this should be a list, not a list.",
      "reference": "Why make this modifiable?"
    },
    {
      "prediction": "I think this should be a better way to do it with the `Erc721Binary` method.",
      "reference": "Why this file is changed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure that we need this"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this going to cause issues in any other places were someone forgets the version? Should we consider also checking for type=project?"
    },
    {
      "prediction": "I don't think this is a good thing to do with the `secretsmanager.GetSecretValueInput` and `secretsmanager.GetSecretValueOutput` and `secretsmanager.GetSecretValueOutput` and `secretsmanager.GetSecretValueOutput` and `secretsmanager.GetSecretValueOutput` and `secretsmanager.GetSecretValueOutput` and `secretsmanager.GetSecretValueOutput` and `secretsmanager.GetSecretValue`",
      "reference": "Does this have retries? Is there a possibility that customer would hit throttle errors here?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `include <sys/cpuset.h>`.",
      "reference": "i noted that we are inconsistent with when we indent includes (see atomics.h which is rather different) and for example cpu.c which is also different. we seem to have 3 styles."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Deleting the files before starting the audit helps avoid stale results if the new file is not created."
    },
    {
      "prediction": "I think this is not a problem.",
      "reference": "Remove this blank line"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This is... quite unconventional (use a map entry as a key). I would suggest making your own data class for the key."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why are these colors needed to be specified here? when are they used?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: no need to change this method."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure how to do this?",
      "reference": "Why a blank line?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why remove the `.html_safe` here? Should we use `sanitize` or `raw` instead? This info comes off of the org edit page and is entered by users."
    },
    {
      "prediction": "I think this is a bug in DYNAMORIO, but it's a bug in DYNAMORIO, but I think it's a bug in DYNAMORIO, but I think it's a bug in DYNAMORIO.",
      "reference": "I think we need some docs about how to set this parameter correctly. Are we OK with changing the public API like this? We probably at least want to make a change notice to the release doc."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "When we undo this for 1.3, do we not need to leave these three entries intact to avoid renumbering of the subsequent constants? If so perhaps the changes to this file should be pulled into a separate initial commit so we can just `git revert` the remainder..."
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "This is never set anywhere in the `cli/gen-api` folder. Should it be?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the client-go/kubernetes/typed/core/v1. I'm not sure if this is the right thing to do with client-go/kubernetes/typed/core/v1. I'm not sure if this is the right thing to do with client-go/kubernetes/typed/core/v1. I'm not sure if this is the right thing to do with client-go.",
      "reference": "All the changes in this commit are mechanical. Produced by the script in the previous commit."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "What's the difference between these 2 versions?"
    },
    {
      "prediction": "I think this is a test case, but it's not a test case.",
      "reference": "@red2k18 Are we sure its correct to only have 1 now?"
    },
    {
      "prediction": "I think this is a bug in RDKit, but it's a bug in RDKit.",
      "reference": "@greglandrum interesting, is this related to #3307 by any chance?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `force_user_id` in the `ENV['FORCE_USER_ID']`.",
      "reference": "Minor: how about moving the trailing `if` to an `elsif` above?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "That's only executed when users switch from 2.2 to 2.3. Please create a new block with code `2050000` for the next release :) Please also adapt the version number in PodDbAdapter"
    },
    {
      "prediction": "I don't think we need to lock the server lock here.",
      "reference": "Safe to reference c.srv without capturing it first under a client lock?"
    },
    {
      "prediction": "I don't see the License at this point, but it may be useful to check the license for the specific language governing permissions and limitations.",
      "reference": "@vincepri blame tells me this was you, any objections to the change?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "@abhinav here is where i need to be able to block/wait until the server is started"
    },
    {
      "prediction": "I don't think this is the case for the `jsonpCallbackParameter` parameter.",
      "reference": "It seems to me as an unrelated change. Could you please revert it?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "~Why are putting all these APIs in their own ~packages~ files? So many more ~directories~ files, to what end? Why not just have them all be a part of the same API file and all live alongside each other so you can easily see them?~ Edit: nevermind, probably works best in separate files."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "This likely needs to be double checked -- I recall being convinced at the time of writing this, but now I am less sure"
    },
    {
      "prediction": "I think this is a bug in the source code.",
      "reference": "For a followup - it is better to use acceptlist/denylist. I realize this is a historical artifact of our codebase."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the file system.",
      "reference": "Looks like glassfish went a bit nuts doing a refactor"
    },
    {
      "prediction": "I think this should be a test for the display property of the element.",
      "reference": "Couldn't you use position:absolute or float to move inline elements outside their parent? Through clipping an child element can also be outside it's parent. There are probably some other ways to do it too. So I'm not sure the assumption you're making here is right."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This could be copied into iceberg code to avoid the spark internal dep? We could use a version check to adjust the method used if needed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This one had me stumped!"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Note that this name differs from the name used as default (and thus used now that you removed this). That should be fine, but wanted to flag it."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why public and not protected?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the current_user.can_super_admin? and current_user.can_super_admin? and current_user.org.present?",
      "reference": "We definitely need to address this duplication after MVP"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `max` parameter.",
      "reference": "This will always generate a label for the first keyword, which means this will be a label linked to no element after the first keyword is entered. This label should be generated inside the `values.map` next to the `<TextField><Input /></TextField>` it is for, because the ID changes based on the index. Also, we have a `VisuallyHidden` component I'd prefer we use over the CSS class. Building as many things out of components is more React-y. Admittedly it's sort of a preference, but it's why we have the `VisuallyHidden` component. So let's use that instead  "
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `roots_xcursor_theme_create` function?",
      "reference": "Does it make sense for this to be fatal? Could there be an embedded application that does not have xcursor themes at all? For instance, compositors without a pointer (like a touch-screen kiosk) will never show a cursor. I think I'm ok with this assumption since it simplifies the code and rootston is assumed to have desktop features, but we should always make sure xcursor is not required to be used in the library."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "would rename to TopicsFilter and original one to SequenceTopicsFilter"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is the idea that ``self.keys[0]`` here normally matches ``init_key``?"
    },
    {
      "prediction": "I don't think this is a bug in NVDA.",
      "reference": "Can this be clarified to \"Exit early when hwnd is the windows desktop handle, UiaHasServerSideProvider would return false anyway.\" ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "I'm okay with leaving VCPULimit and MemoryLimit on our internal model"
    },
    {
      "prediction": "I don't think this is the default rule priority for K8s NetworkPolicy rules.",
      "reference": "5 or 10?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Should we explain more here?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I've been struggling with this on my cloud-init integration work as well. In addition to info that is currently stored in the cluster providerstatus, we also need some of the info that is available within the base cluster object as well. I think it would make sense to unify the machine and cluster info needed into a consolidated struct rather than continuing to add additional disparate structs."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Why not `@InternalApi`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "FYI: `GenericMeta` is renamed to `_GenericAlias` in Python3.7."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "So this hides the link to re-order sections on Historic Templates? Good catch, Just checked on DMPonline and hitting that throws a 404"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is `Reporter#reset` no longer used? If so, can we remove it?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "same concern here about difference in the write scalar implementation. I am not sure if this could present a consensus problem or not"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we remove this file?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Why listing only first error reason (`ErrStatus.Details.Causes[0].Message`)?"
    },
    {
      "prediction": "I think this is the default value for `USE_STARTING_SEQUENCE_NUMBER` and `USE_STARTING_SEQUENCE_NUMBER_DEFAULT`.",
      "reference": "Now that this is true, do we have to ignore it with V1 Tables?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "prefer if (condition) { stuff; } to if !(condition) { continue; } stuff"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Should this section not be converted to a secondary action list?"
    },
    {
      "prediction": "I don't think this is the case for a pinned tab?",
      "reference": "This askes a blocking question, which means a local Qt eventloop will be running. While this is unavoidable sometimes, the async functions should be used whenever possible (`message.confirm_async` in this case). This means: - Split everything after this question in a separate private method (you can probably just call it `_tab_close`) - If the tab is not pinned, just call `_tab_close` directly - If it is pinned, call `message.confirm_async` with `yes_action=self._tab_close`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Can we deuglify this?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `partialFunction`?",
      "reference": "@skestle Just recognized that the `::apply` is not necessary. Does it compile if you leave it away? Could you please check that, I'm on vacation and have no IDE at hand... Thx!"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Looks like this is an unnecessary change."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This one won't change as the resource is not included in the project getting tested with the composite root."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "We have `stdbool` imported, might as well use that for clarity."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we not also have integration tests for postgres?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I think its safe to remove this if we're removing `reIndex` outright. The description shows us that the test is \"An example showing how to force a reindex of a collection\""
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Can you make this hexadecimal to match the other constants?"
    },
    {
      "prediction": "I'm not sure if this is a deprecated file.",
      "reference": "Can this get moved to `Bolt::Project#validate`?"
    },
    {
      "prediction": "I think this should be a List<T>, List<T>, List<T>, List<T>, List<T>, List<T>, List<T>, List<T>, List<T>>",
      "reference": "I'm pretty sure it doesn't harm, but don't we have a second pass here with the reverse() operation?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is not a standard capability and should be hidden behind a vendor prefix: -chromium-takesHeapSnapshot"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This shouldn't work with pointers -- prefer references unless you can meaningfully pass `nullptr`. The address-of operator here is clunky at best."
    },
    {
      "prediction": "I think this is a bug in GCC 11.2.0.",
      "reference": "Sidenote: some day we'll drop the avr-gcc and avr-libc dependencies so that this case becomes supported."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "do we still need this method?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `xformedEffUpsert()` method.",
      "reference": "It's better to not leave this old code here... it just clutters things up and makes reading the code more confusing. We can always recover the old code from the repository if needed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Again, you don't want to depend on glassfish."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This shouldn't be required. What was going on here?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Why add this here?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `ReturnType.Headers.AsNullableType(HttpMethod != HttpMethod.Head)` and `ReturnType.Body.AsNullableType(HttpMethod != HttpMethod.Head && IsXNullableReturnType)`.",
      "reference": "nullability does not apply to headers type (that is always an object)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do we also need to add the iova, or is that done somewhere else?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "why change this?"
    },
    {
      "prediction": "I think this is a bug in h2o_time2str_rfc1123 and h2o_time2str_log.",
      "reference": "If there is no guarantee that tv_sec is of type `time_t`, IMO you should copy the value instead of enforcing a pointer typecast."
    },
    {
      "prediction": "I think this is not a valid path?",
      "reference": "Should we validate the suffix before going to the filesystem?"
    },
    {
      "prediction": "I don't think this is the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's the default, so it's the default.",
      "reference": "It feels like we should be working to reduce/eliminate our global vars. I'm not sure it adds much here. Any objection to just removing it?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "did you consider using AR enums for this? would give us all the boolean methods (`weekly?` etc) for free"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This may change \"\" into None. Better return filename."
    },
    {
      "prediction": "I don't think this is a good idea to use the `skip_devices` flag.",
      "reference": ":+1: That does resolve my security concerns about this feature."
    },
    {
      "prediction": "I don't know how to handle this, but I don't know how to handle it.",
      "reference": "Could you add a docstring?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't this still be `Region()`?"
    },
    {
      "prediction": "I think this is a bug in QTreeView.",
      "reference": "This shouldn't be here but `self.connected = None` in `__init__` instead, otherwise that'd be an attribute which is set this way in _every_ instance of that class (i.e. a class rather than an instance variable). I'd also say let's make it \"private\" (i.e. `_connected`) and please add a quick note about what it is to the docstring of the class."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "This would be better served as a method/property that is set when people don't want to a window."
    },
    {
      "prediction": "I don't think this is the case for a non-page streaming method.",
      "reference": "I was dubious about putting getNonStreamingMethods in the context, but after some thought, I have decided to embrace the approach. In this particular case, the loop is supposed to be over page streaming methods. So, could you add a getPageStreamingMethods() method in the context, use it here, and remove the isPageStreaming() check below?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "LooseVersion class can help here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`const Dims zeros(shape.size(), 0);`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `--profile [COUNT]` or `--profile [COUNT]`?",
      "reference": "Would be good for this not to say `10` anymore..."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `adsense` component.",
      "reference": "See above, we don't need to pass the module name here."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "This is random line :-) overridden String type by custom trimmed - please change that commit message to something like \"introduced custom String type with automatic trimming\""
    },
    {
      "prediction": "I think this should be a function, but it's not a function.",
      "reference": "My personal taste: \"depreciated\" -> \"deprecated\""
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "this includes the port as well right? should the name be `destinationServicePortName`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We can import all of them in one line."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "this was wrong, the rest were just inconsistent :)"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I gave them the EXACT SAME NAMES in my branch :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What would you think stat'ing the directory first before doing the log+mkdirall and only proceeding if the directory does not exist? The logging might be less confusing (I'd be wondering why it was logging that it was creating the directory when I knew it already existed)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Sorry about the confusion, I'm trying to address that in the PR follow-up. If we ever have `Span` objects, then accessing their properties is going to be safe. The only question remaining is \"What is the runtime type for Scope.Span?\" and we just have to account for it when it is `Datadog.Trace.Span` and when it is not"
    },
    {
      "prediction": "I'm not sure if this is a test, but it's not a test.",
      "reference": "I was using this imports for writing the results to file to more easily check that it was valid JSON. You can probably remove these `java.io` imports."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You should probably include a `json:...` annotation here."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "can container ID > 255 chars? why are we doing this check?"
    },
    {
      "prediction": "I'm not sure if this field is prohibited when :other is in :values.",
      "reference": "*\"This **field field** prohibits :other from being present.\"*, **field** word repeated is right?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: no need to add an alias for this case."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `QUIC_GO_LOG_LEVEL` environment variable, so we can't use `QUIC_GO_LOG_LEVEL` instead of `QUIC_GO_LOG_LEVEL` instead of `QUIC_GO_LOG_LEVEL` instead of `QUIC_GO_LOG_LEVEL` instead of `QUIC_GO_LOG_LEVEL`",
      "reference": "Or `QUIC_LOG_LEVEL`. Which one do you prefer?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Minor: you can set it to byte here and only set it to *virtualDiscDesc.CapacityAllocationUnits if that's not nil/\"\". Saves two lines"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "While reading this I found that it makes actually little sense for \"beers\" to have a \"fingerprint\". We might want to do another pass on the examples here to use something that actually makes more sense to the reader. This could be done in another issue."
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Thank you! That's better, especially the conversion test should not test the mkString method :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You're basically converting client to screen coordinates here, doing it manually. Is there a specific reason why you aren't using clientToScreen here? Does it fail?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This needs to be done for server-side copies too, earlier in the function."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we want to add in `profile` here as well so we request access to the end user's default profile claims like name?"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "I am not sure what the difference between approving and full approving is..."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please back out the import changes in files you haven't touched. I think these happen if you run goimports without having the vendor directory populated"
    },
    {
      "prediction": "I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case.",
      "reference": "Many tests in this class seem to have just been fortunate that `SolrIndexSearcher` ignored `fl` and retrieved all fields when not using lazy loading."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is this really needed?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is this necessary with line 38?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "DO we want to have >= here? Or =="
    },
    {
      "prediction": "This is a hack.",
      "reference": "Can you also add this `\"version\"` tag to the CoreTags? Now that we're targeting the service/env/version trio"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This entry will be incompatible with the currently implemented formatting rules. Maximum 120 characters per line."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `--preserve_host_output` option.",
      "reference": "Let's call this color_host_output or some such - preserve_host_output makes it sound like you won't get any output without this being set."
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `role` attribute?",
      "reference": "suggestion: if we perhaps make `attributes` a getter in `virtualNode`, it does look seamless to access the property, same as what we have done for `isFocusable` or `tabbableElements`. `node.attributes` can become `virtualNode.attributes`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think a float value fits better."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This should be (POST,DELETE) `/pss/subscribe/{topic}` for subscriptions and there should be `/pss/send/{topic}` for sending."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Closing over the closure arguments is a neat trick :+1: Love it :100:"
    },
    {
      "prediction": "I'm not sure if this is the case sensitivity is on, but it's not the case sensitivity is on.",
      "reference": "Does this need to be a block or can it be an expression?"
    },
    {
      "prediction": "I'm not sure if this is a post request?",
      "reference": "req.getQueryString() != null is not necessary since same check is already done in allowedPostRequest"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "As per go/actools-regapic-design, in the final product, generated GAPICs must be able to support multiple transports if supported by the API. For Java, we'll support this in the microgenerator; the monolith generates single-transport GAPICs. For PHP, the situation is likely similar, though on a longer timescale. All this to say that I would appreciate structuring the code in terms of \"supports REST\" rather than \"REST only\", but only where this doesn't require undue work. For everything else, please add a TODO to the effect of \"we're generating single-transport GAPICs for now, though in the fullness of time we'll generate multi-transport GAPICs.\""
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's a string, so it's not a string, so it's a string, so it's a string, so it's a string, so it's not a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "here is `:seconds` missing again"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `stub_mail_method(klass, method_name, deliver: true)` and `stub_mail_method(klass, method_name, deliver: true)`",
      "reference": "Changed this helper to also get class name."
    },
    {
      "prediction": "I don't think this is the default.",
      "reference": "I think there's another spot for this in DefaultCapabilityMatcher"
    },
    {
      "prediction": "I think this is a bug in pony_actor_pad_t.",
      "reference": "Why the rename from PONY_SCHED_BATCH ? ACTOR_DEFAULT_BATCH is less meaningful to me than SCHED_BATCH."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Let's be sure we have an issue that tracks this, filed against testnet."
    },
    {
      "prediction": "I don't think this is a `Buffer` or `Buffer`?",
      "reference": "There should be no space before !Buffer"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Same here, we need the default padding for this story."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think this should go away, its noise in the grand scheme of things."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Maybe just call `ioutil.WriteFile` with 0 bytes? And Make an error log `log.Error` if any error occurs."
    },
    {
      "prediction": "I don't think this is the case where we want to use the `setIeService` method, so we can't use `setIeService` to use the `setIeService` method, so we can use `setIeService` to use the `setIeService` method, so we can't use `setIeService` to use the `setIeService` method, and `setIeService` to use the `setIeService` instead of `setIeService` instead of `setIeService` instead of `setIeService` instead of `setIeService` to use `setIeService` method.",
      "reference": "`this.ieService_` should be initialized to null in the constructor."
    },
    {
      "prediction": "I don't think this is the right thing to do with the IPVS connection.",
      "reference": "I just noticed that we use Return here, when we have logically allowed a packet, whereas in the forward chain we use AcceptAction. Do you know why that is?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is public method , we need to deprecated this method first and add new updated method for it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think that you don't want to have these workarounds; you want to make sure that the relayTemplates is configured correctly. If not, we need to fix it there."
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "This field is not needed."
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `cancellation.schedule` method.",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "move to line 18 below"
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "Simple Storage **Service**"
    },
    {
      "prediction": "I'm not sure why this should be done here.",
      "reference": "Thats odd, I'd actually not expect this output at all..."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "As a side note, I get why this is up here (sort order), but it'd be easier to not forget to update it if it were down next to `1.x` -- would it be acceptable to make that change the next time I make this sort of PR? :smile: :innocent: (don't want to hold this one up since folks are blocked on getting this one in, it's a pretty superficial change, and I probably won't have cycles again for a few days to update the PR with the change :sweat_smile:)"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "this class is permissioning so let's keep \"Onchain\" here"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "we can be more specific to call out the it is \"AutoRest C# code generator\"?"
    },
    {
      "prediction": "I'm not sure if this is a virtual node.",
      "reference": "Ditto for not adding this to the axe namespace."
    },
    {
      "prediction": "I don't think this is a bug in the package.",
      "reference": "Should we just remove this file? Having it present but empty feels misleading"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would it make sense to include an `Untrust` as well? If I were playing around with this on the CLI I wouldn't want to make a change I couldn't undo."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It might be better to call this `$createRecordMethod` since it's not a full PHP callback, just a method name for the plugin manager."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "remove this line"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I've never seen this syntax before, it's still just an array, the difference is that it's an array of MainMenuItems instead of an array of arrays."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: to match the others: s/private/Private/"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe just IEnumerable? Not sure myself."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "do we need this change?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Would want @matthiashanel to have a look since if I recall he had to add the shallowCopy() to fix some bugs during reload. That being said, since I believe the $G account cannot referenced in configurations, this should not be a problem, but Matthias has looked at this in more details in the past."
    },
    {
      "prediction": "I don't think this is a good idea to do with the `GetVolumeStatus` function.",
      "reference": "The descriptions are incorrect"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "if we are returning the `ws` here when passing in `se:cdp` we can just return it straight or do we have to make a request to get the `ws` address?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Please only indent this by four spaces."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What's the reason behind these characters?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `approver_approvals.each` method.",
      "reference": "Minor: The name of this specs seems a little off now"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'd suggest using `ast_error_continue` here to get the `apply` message in the `Info` part of the error report."
    },
    {
      "prediction": "I'm not sure why this is the right place.",
      "reference": "If we decide to change the name of the .ini setting, we might also want to review the naming of this property and related code. Maybe a simple `getOptions` or `getSettings` would be more concise than `getTabDetailConfig`. At very least, I don't think we need Tab in the method name since the method belongs to a helper with \"Tabs\" in the name."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Use const for \"user\", same as below"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "->setUnsubscribed(false) would be better :)"
    },
    {
      "prediction": "I'm not sure if this is a string literal, but it's not a string literal.",
      "reference": "I now think singular `Sport` is better, but I will wait for the first round of feedback before updating."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Don't you need = something ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like this could be `const` (I realize it wasn't like that before)?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe just `FAILED`. We can't be sure loading was the thing that failed."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with it.",
      "reference": "You have replaced single quotes with double ones, this fails linting and our current coding style. Please fix this, otherwise it's a whopping of 1200 LoC while in reality it should be rather small."
    },
    {
      "prediction": "I don't think this is the default value of PREF_CURRENTLY_PLAYING_MEDIA.",
      "reference": "@danieloeh @TomHennen. Some of these files are using spaces, the others use tabs. Is there a project wide preference? I personally like spaces, because they are consistent across editors"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to change the `counter` to `nil`?",
      "reference": "I guess this is ok for backwards-compatibility? Maybe it'd be better to check arity in the helpers? Or just call it out in the release notes, because there are at least a couple projects on github that overrode `initialize`.."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "At some point, we would like to get rid of these custom injections as well. Looks Ok for now."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: Not a fan of \"fix\" in the name, but don't have a better suggestion  "
    },
    {
      "prediction": "I'm not sure why this is a bug?",
      "reference": "Since we're calling `self.tab_url(idx)` a third time here already, can you please add a `url = self.tab_url(idx)` somewhere above (e.g. after all the `fields[...] = ...` assignments) and change the calls here to `url.host()` etc.?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "alphasort this import"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "remove this file!"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "You don't need to say `rune(' ')` - `' '` is already a `rune`."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We can't freeze this and then add something to it in the next line. The `freeze` on line 43 is sufficient. If Rubocop flags this we need to exclude it."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "We call it Kind2 and move out of the `javaslang/control` package into the `javaslang`package. Maybe I will later generate Kind1..Kindn but that's another story."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i think it might be nicer to have a message like: `database capacity: %d chunks (%d bytes, %d megabytes)`. counting in bytes is so 90s :)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `azkaban.jhs.job.link` or `azkaban.shs.job.link`?",
      "reference": "The '.' in the key names are used to separate namespaces, NOT to separate words. How about azkaban.external_resources.resource_manager? ---- Why is it better than using the full name in the variable name e.g. RESOURCE_MANAGER_LINK ?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with OpenTelemetry.Trace.Samplers.",
      "reference": "This seems to be duplicated with line 19?"
    },
    {
      "prediction": "I don't know how to use `wx/xlocale.h`? I'm not sure how to use `wx/xlocale.h`? I'm not sure how to use `wx/xlocale.h`? I'm not sure how to use `wx/xlocale.h` and `wx/xlocale.h` and `wx/wx/wx/wx/wx/wx/wx/wx/wx/wx/wx/wx/",
      "reference": "This is wrong. xlocale.h is needed on OSX and maybe elsewhere too. This needs a test in configure to see if xlocale.h and uselocale() are available and an #if test here. Also, the NO_PER_THREAD_LOCALE stuff in configure.ac needs to be updated to include test for uselocale()."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why did you have multiple function calls here instead of having one long array of supported mimeTypes? In line with your PR here, I think we might eventually see inline videos or inline pdf. It would be great to generalize this a bit."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "nit: shall we keep alphabetical order?"
    },
    {
      "prediction": "I'm not sure if this is a real object, but it's not a real object.",
      "reference": "We could just move the check for function into `typeForConstruction` to make this a one liner every time we need to do this."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "A correct by unrelated change. We'll slide this one in without another word ;)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I feel that a slightly safer way is to do if (param_.has_device_id()) { Caffe::SetDevice(param_.device_id()); } just in case a user has hard-coded a device id outside the solver and does not specify the device id in the solver param. Currently, if nothing is set, the solver will always use the 0th device, which might not be desired."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "let's replace this example with something that won't fail in Python. Like \"for+if+print\""
    },
    {
      "prediction": "I don't think the precision is a string?",
      "reference": "Please remove the brackets and use `string_type` from `compat.py` module instead of `str` in `isinstance()`."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "line is 143 characters (from `lll`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It should follow a `continue`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Should this be DBWorkingDir?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is the case.",
      "reference": "I think you can remove the whole line."
    },
    {
      "prediction": "I don't think this is a bug in iotexproject.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I'm not sure why this is a string, but I'm not sure why this is a string, but I'm not sure why this is a string, but I'm not sure why this is a string.",
      "reference": "Not a big deal, but what is the value of adding this status condition for a failure to delete a client? It has some value for a dataverse admin, to know that the last attempt to harvest from a certain server resulted in a failure. Is it really useful to know that an attempt to delete a client failed? - should the startup check simply remove the \"delete in progress\" flag quietly instead? After all, seeing how the client is still there makes it somewhat clear that the attempt to get rid of it didn't work out, so they should try again? I may be missing some situation where it could actually be useful - so I'm open to hearing it."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Can we also update the equality delete branch below?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This doesn't solve the entire problem we talked abut yesterday, right? Because it's possible that the step itself didn't skip, but rather that it chose not to yield the output in question?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I also do not see any usages of this import. Is this a fix for a crash?"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to update the desired status for awsvpc network mode.",
      "reference": "Feels like this needs to be invoked in `PostUnmarshalTask` since that's where most of the task setup happens."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I wonder what would happen if the granteeName becomes DB__ROOT but the granteeID is not DB__ROOT ID (33333) but something else."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Feel like this should probably come into this tool as a flag rather than it just grabbing an env var internally?"
    },
    {
      "prediction": "I'm not sure if this is a WebDriver instance.",
      "reference": "This should only be sent if the driver is speaking to a W3C conformant remote, so we need an if-condition check like we have in the Python bindings."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: folders are always a numeric ID, projects as given by CAI use project number for ancestry"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "is this used anywhere?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "change pkg_errors to errors. Keep it consistent across all the files."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't see any test cases which would test that fix dates are set properly on review status changes / storage events. For this reason please create some more test cases and also check my scenarios above."
    },
    {
      "prediction": "I don't think this is the default response.",
      "reference": "This belongs to SwaggerModeler.cs `public override ServiceClient Build()`"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "We could go further and directly give the tips of the `columns` property for someone (like me) who would like to specify some column width and let the others be autosized."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think a `std::copy` with `std::back_inserter` will get this done in one call."
    },
    {
      "prediction": "I think this is a bug in QUIC 36.",
      "reference": "In the future: s/QUIC 36/Version36/ to make grepping easier"
    },
    {
      "prediction": "I don't think this.state.formState.checked is the same as this.state.formState.checked.",
      "reference": "This is an example of why I prefer a flexible custom `render()` solution   'on'/'off' may not be the right value for every application. You have to make a lot of decisions even for very simple form fields :("
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "we should also skip the e2e flow aggregator tests if the Flow Exporter feature is disabled."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should initialize the observation in the constructor of the Script class - otherwise, we don't have this feature for mitmdump."
    },
    {
      "prediction": "I think this should be a list of tuples, not a list of tuples. I think this is a list of tuples, not a list of tuples.",
      "reference": "I would remove this line. Otherwise looks fine cc @ueshin"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would it be better to remove that line alltogether if it not directly relevant?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Does \"FPU\" here include XMM/YMM/ZMM SIMD and not just x87 FPU/MMX?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure if we need to store path as bytes, and then decode/escape it when printing or just store it as a unicode string (as done here.)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why is this flipped? Looks unrelated and our pattern is `expected == returned`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Can the `h5` tags be pulled outside of the `if` block?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to use, but I'm not sure if this is the right thing to use.",
      "reference": "From @PetrHeinz review: this should be also aliased (`ImageDirectoryStructureCreator`)"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Isn't AdditionalTags already of `Tags` type? If not, we should make it so, if it's not a breaking change"
    },
    {
      "prediction": "I'm not sure if this file is used.",
      "reference": "Add blank line below license header."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Perhaps this could be moved into `InitPWM`? I suspect not initializing the clocks will reduce power consumption."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "I believe this `order` isn't tested."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "No idea why it ended up in the code. You can remove the entire line."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "\"i\" and \"From\" is a bit duplicate, and should it be singular given the method name? I mean \"fromPeer\" or just \"from\"?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Did you verify this isn't going to break any existing test assumptions? We probably shouldn't modify this as we don't know what impact this is having on existing tests. It may invalidate a test that has different expectations of the scopes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "technically not necessary since reading from a nil dictionary will always return found = false, so this should already be handled"
    },
    {
      "prediction": "I'm not sure why this is a bug in the future, but I'm not sure if this is a bug in the future.",
      "reference": "This can return bool. RelaxedReclaimPurge(nodeID string) (bool, error)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is there something we can do to make this automatic? At the very least, can we add Shanghai, Cancun, etc. here now so that we don't forget them?"
    },
    {
      "prediction": "I'm not sure why this is a bit of a hack, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "For boolean values, I'd rather have `argparse.SUPPRESS` as default value. No need to have a `(default: False)` in the help if it's a toggle."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The genesis block needs to exist in the store the fetcher pulls from, this is because the fetcher will stop fetching when it finds a block it has seen before and this can sometimes be the genesis block."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we do the same for os.Mkdir(criuOpts.WorkDirectory, 0755)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@bbondy Two messages because the label and description differ very slightly in their wording..."
    },
    {
      "prediction": "I don't think this is the case for AVX-512 registers.",
      "reference": "\"currently\" implies it should and will be changed: so TODO i#?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `Ember.computed`?",
      "reference": "This should be `computed('i18n.locale'....`"
    },
    {
      "prediction": "I don't think this is a test case.",
      "reference": "Wait, does this not work if we do `btl.reload`? That seems odd that we have to have the object in the same state."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I seem to recall this being the cause of a bug at some point."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Can you remove it from the menu instead of setting it hidden? Or are there any other trouble?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `gomock.mock.gomock`?",
      "reference": "And for \"execution \"."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do agents usually download these from puppetserver when applying a catalog?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This should be `return (ev->flags == ASIO_DISPOSABLE);` because `ASIO_DISPOSABLE` has a value of `0` as defined in the enum in `asio.h` and because when `ev->flags` is assigned `ASIO_DISPOSABLE` it is assigned as `ev->flags = ASIO_DISPOSABLE` unsetting any other flags previously assigned."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `options.DefaultCollectionPeriodMilliseconds` in the future.",
      "reference": "this is not required, right? its the default already..."
    },
    {
      "prediction": "I don't think this is a problem with the server side error.",
      "reference": "\"contingent to\" -> \"contingent on\""
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Does pandas throw an exception like this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The point of the exercise has been to eliminate CoreChecks as an object dependency for DescriptorSet et. al."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we need to make so much more of this ScanContext public?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "is choice_name not needed anymore?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "Is this the right place to do the validation? If a user adds a bad property or performs some schema update that causes a validation error, that would break all writes to the table. To me, it doesn't seem like we are catching the problem early enough and possibly allowing a typo to break scheduled jobs. What do you think about adding this validation when altering the table? `UpdateProperties` could check whether any properties starting with `write.metadata.metrics` were modified and run this. Similarly, `UpdateSchema` could run this as well, although I think that we should probably modify `UpdateSchema` to simply update the properties for column renames (if that's easily done)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this necessary? Just in order to get an indexed loop?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "instead of using `prometheus.Gauge`, using `promethus.Counter` will be better."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "maybe we should have a unit test for this and then just test one case in `spec/services/ncr/approval_manager_spec.rb` ?"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `approval_id` field?",
      "reference": "Why is this necessary?"
    },
    {
      "prediction": "I think this is a bug in iceberg, but I think it's a bug in iceberg, but I think it's a bug in iceberg, but I think it's a bug in iceberg, but I think it's a bug in iceberg.",
      "reference": "Minor: If this is going to be public, we should fix the name. `get` doesn't add any value. How about `distributionModeFor` instead?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This needs a more self-explaining name. Maybe `.is_focused`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "minor: I'd add a space between `,` & `'paginggroup'`."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `--reupload` option, but it's not the right thing to do with the `--reupload` option.",
      "reference": "\"Re-upload all fragments (even if fragment is already in registry)\""
    },
    {
      "prediction": "I think this is a bug in Prometheus.",
      "reference": "I don't see us ignoring the field. Are we sure Prometheus wouldn't refuse to load the rules?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I wonder if we can just check if the mSession is active and then only call `setActive(true)` and `callSurfaceChanged()` if it isn't?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "A default value of 100 MB maybe too small. I understand that this is good for mixed workloads, but do consider than plans with Unpack, especially when used for insert/upsert are simple. Unpack is always serial and part of master exe. Often there is only one in a query. The cost of having a low value here seems to be that queue length from unpack could be limited by this when we are loading a table with wide rows (even if actual data in row is not wide). We know from performance runs that queue length is critical to upsert load performance. This is a hunch on my part and could be misguided. It will be good to performance test for upsert of table with wide rows, if you think that is worthwhile."
    },
    {
      "prediction": "I think this is a bug in the future. I think this is a bug in the future. I think this is a bug in the future.",
      "reference": "think we should pass in ctx, and use ctx.GreenlandHeight inside bucketPool to determine if create or not"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "A correct by unrelated change. We'll slide this one in without another word ;)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the form.",
      "reference": "Why remove this?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I still see some usages of not namespaced variants (look for Twig_ in project, about 42 matches). Is it intentional?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Is this a new dependency? Does this require a dep update?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "> opts.generate_hexfloat_in_json && **IsFloat**(type.base_type)"
    },
    {
      "prediction": "I think this should be a string, not a string.",
      "reference": "As an alternative to this, we could also create a new method, like `Common() *AppManifest` This way we don't have to add a new method to the interface everytime we add a new field to the `AppManifest`. This is a nit though so it's up to you."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "As long as we have this feature as an inline script, I'm inclined to remove the dependency here. I'd suggest that we just try to import harparser and pytz and throw an error instructing the user to install the dependencies (catch for `ImportError`). In the long term, we probably want to include that in the mitmproxy core, but we first want to introduce a clean extension interface before that's going to happen. As soon as said interface is there, porting the inline script and adding the dependency again should be a breeze."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "makes it work nice with vscode. all logic is now in `.gulp/*.iced` files"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "should a similar change be done for findElement?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "`+` -> ` + ` I guess. Same below"
    },
    {
      "prediction": "I think this should be `opts.feeSat` or `opts.feeSat` or `opts.feeSat` or `opts.feeSat` or `opts.feeSat` or `opts.feeSat`",
      "reference": "`typeof` is not a function - its an operator, and the standard way to use it is as `typeof foo !== ...` (i.e. no parenthesis). Also, I would personally use `opts.fee != null` instead (with a non-strict comparison, which also identifies `undefined` values because `null == undefined`)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is there a reason why you're not using Rspec `skip`? It allows to specify message and makes it clearly visible in test results which tests were skipped."
    },
    {
      "prediction": "I don't think this is a problem with the `firstSyncSetsSuccessTime` field, but it's a `firstSyncSetsSuccessTime` field.",
      "reference": "how about \"all matching SyncSets and SelectorSyncSets\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is the logic behind `ReadVectorSize` reading `CountElement64`, then skipping `T` (in this case `unsigned`)? Naming doesn't cover what's actually happening here. Ideally I'd also take this through a `files` layer, any input as to how?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This looks like an unused import to me?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`RW` means read/write. Why do we have it here, as part of a func name?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd keep this at `info` level..."
    },
    {
      "prediction": "I think this is a bug in h2o_http2_conn_t, but it's a bug in h2o_http2_conn_t, but it's a bug in h2o_http2_conn_t, but it's a bug in h2o_http2_conn_t, but it's a bug in h2o_http2_conn_t, but it's a bug in h2o_http2",
      "reference": "I think you missed this."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `CopyToAsync` method.",
      "reference": "List all of the current TFMs so we know if this gets outdated. E.g. this breaks if we add 2.2."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "here, you want to use req.GetXattrOpt() referring to the in line 514 of api.proto. This will be nil if not provided. See the example above on line 801 on this file"
    },
    {
      "prediction": "I think this is the case where we should skip the current episode.",
      "reference": "I think this should be done outside LocalPSMP, but in `getNextInQueue`. The reason is that I want to reduce the dependence of the media players on the preferences and database. Also, it will then probably work on Chromecast."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Please remove it or remove all `std::` namespace prefixes."
    },
    {
      "prediction": "This file should not be used in any way.",
      "reference": "wait! I'm confused - is that an empty file ?!"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "These should all call `findUpVirtual`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This changes the behavior. Original behavior was \"set if not set\", while new is \"just set\"."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Let's keep using the regular expression to make sure that the token is well-formed. I think the regular expression should be altered instead of doing a substring."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `back` and `delegate` parameters.",
      "reference": "All the operations are delegated to this entity, hence the rename. `back` can have too many meanings."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the user environment?",
      "reference": "@trevor-vaughan it looks like the spec failures are caused by the fact that although it was a great idea to put the guard clause here first & get the error case out of the way, the main code path has been erased when I assume it should be just below the guard clause."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Could you delete this constant?"
    },
    {
      "prediction": "I'm not sure why this file is in the project root.",
      "reference": "looks like this snuck in from your other change?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "These env vars are not set in any CF environment, on purpose, because we are moving away from using env vars to store role-based information and instead using the database. So in a CF environment, the wrong emails get used (the defaults, rather than what is in the db)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "this partial is used also for previewing a template, did you test if still works?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the app name?",
      "reference": "Would it be better to put like `Which Dockerfile would you like to use for %s?`"
    },
    {
      "prediction": "The `options.writeConcern` option is deprecated, please use `options.writeConcern` instead of `options.writeConcern` instead of `options.writeConcern`",
      "reference": "You mistakenly removed `/docs` here, please add it"
    },
    {
      "prediction": "I think this should be a list of offsets for each file block.",
      "reference": "I missed this earlier, but why does this say \"file blocks\"? This should probably be \"recommended split locations\"."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please change this to non-exported."
    },
    {
      "prediction": "This is a hack.",
      "reference": "This is ignoring compatibility: it needs to check the size to ensure this field exists in the client."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Do all the prepare authors also need to be unique? Or is it enough the we have minimumPrepareMessages. I guess I'm wondering if need a hasDuplicateAuthors check like in the RoundChangeCertificateValidator."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "we had some situations where we merged some promql bits then took them out. i'm not sure what's going on here, but unless your code actually needs promql (probably not?) let's remove this line."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Annotations in this hunk should follow PhpDoc style (above the occurrence, type first)"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "This is an improvement - thanks! Could we rephrase slightly to not use the phrase \"is not supported\" -- instead stating _WHAT_ isn't valid please? e.g. maybe `String.format(\"Unsupported BoundType provided: %s\" type)` or something like that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: `procfd` seems more appropriate now?"
    },
    {
      "prediction": "I don't know why this is needed.",
      "reference": "Let's not call it django. Maybe `auth_provider_headers`? `auth_headers`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we mention TLS map here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "remove this empty line pl0x"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `on_approver_removal` method, but I don't think it's the right thing to do with the `on_approver_removal` method.",
      "reference": "Why not have this in the `Dispatcher`? Doesn't seem like NCR-specific functionality."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If you need only test db, use `memdb.NewTestDB(t)`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I'm not sure I like setting the IsEmpty property true for upgraded connections since it feels a middle misleading. Maybe we can leave the ForUpgrade class as is and change this condition to `if (!messageBody.IsEmpty && !messageBody.RequestUpgrade)` to make things more explicit."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "git checkout since this is unrelated to this PR? (running migrations also changes this for me -- not sure why it keeps going back and forth"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Is this change needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Isn't the % 128 redundant here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Are you testing that the values are always false? I think you should test for setting values to true or false, right? Who is going to take action with these values?"
    },
    {
      "prediction": "I don't think this is a bug in MPI.",
      "reference": "Please change MPI to CCTOOLS_WITH_MPI"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why you can't use function here?"
    },
    {
      "prediction": "This file is distributed under the Apache License, Version 2.0 (the \"License\");",
      "reference": "We should scope this down to only the methods we use."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Oh, thanks for catching - I thought I've catched all after changing `mkString(infix, prefix, suffix)` to `mkString(prefix, infix, suffix)`."
    },
    {
      "prediction": "The `status.certificate` field is set to `true`.",
      "reference": "Suggestion: `.. the CertificateRequest is ready for signing` - could we perhaps word this differently? I understand that in this case it will be the associated X.509 certificate that can now be signed, so maybe `the certificate is ready for signing` ? (Same with `CertificateRequestReasonDenied`)."
    },
    {
      "prediction": "I don't think this should be a function.",
      "reference": "We should use `! isValidAccountID( accountID )` for the `accountID` checks."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "That alternative does seem better. Did you want to try to do it in this PR? It makes sense to me that the inventory would always be available before creating the executor."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Missing the `-y` argument which all other `apt-get install` commands have."
    },
    {
      "prediction": "I think this is a bug in VUID-VkGraphicsPipelineCreateInfo-subpass-00759. I think this is a bug in VUID-VkGraphicsPipelineCreateInfo-subpass-00759. I think this is a bug in VUID-VkGraphicsPipelineCreateInfo-subpass-00759. I think this is a bug in VUID-VkGraphicsPipelineCreateInfo-subpass-00759.",
      "reference": "So I think we are going to settle on the \"concise and elegant\" `PRI` macros as they are the safest option for now. Even though they make my eyes bleed a little..."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Interesting, was this needed for a test case to pass? I figured if there is no opening brace, there is definitely no placeholder -- we don't even have to check for a closing one."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think we want to provide getAction API instead"
    },
    {
      "prediction": "This is a hack.",
      "reference": "There is also `winVersion.isWin10`. I think this should be converted to use the helper function. The helper has a note that it doesn't work in source copies, but looking at the implementation it looks equivalent to what you have here."
    },
    {
      "prediction": "I don't think this is the right thing to do with `RSpec.config.use_transactional_fixtures` and `RSpec.config.use_instantiated_fixtures` and `RSpec.config.use_instantiated_fixtures` are the same as `RSpec.config.use_transactional_fixtures` and `RSpec.config.use_instantiated_fixtures` as `RSpec.config.use_instantiated_fixture_path`",
      "reference": "This doesn't seem like it should be part of this pull request."
    },
    {
      "prediction": "I don't know why this is the right thing to do with the current user?",
      "reference": "Is the idea that `@product` (and `@workshop` for `workshops_controller`) would eventually go away here?"
    },
    {
      "prediction": "I think this is a bug, but it would be better to use the `bscMainnetPreverifiedHeight` instead of `bscMainnetPreverifiedHeight` instead of `bscMainnetPreverifiedHeight` instead of `bscMainnetPreverifiedHeight` instead of `bscMainnetPreverifiedHeight` instead of `bscMainnetPreverifiedHeight` instead of `bscMainnetPreverifiedHeight` and `bscMainnetPreverifiedHeight` and `bscMainnetPreverifiedHeight`?",
      "reference": "We should add those only once we have successfully synced to the BSC main net, we have a utility to generate those. Please remove for now"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "And how is that related?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "this should be required"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This appears to be unused"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I think that \"table's state\" isn't clear enough. How about \"history of the table's current snapshot\" like the one below?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This looks like a bug: pretty sure there are scatter-gather instructions on AArch64. Ditto below."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "No need to change this: id love if we changed as a team to unkeyed fields, it ends up catching a lot more at compile time, at minimal cost"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Should this be in the parent struct? `AppManifest` since it's embedded to `LBFargateManifest` it'll get the method as well."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "\"Openvpn check\" we could move this to separate prefix."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "body is being used here for the first time without every being populated. This will error. To run tests do `./go clean test_py` and that will run the Firefox tests"
    },
    {
      "prediction": "I don't think this should be called in the same place.",
      "reference": "We don't return now?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it's not the right thing to do.",
      "reference": "This might end up not doing exactly what we want (the retry only picks up the `go get`, not the `go build`, due to the `&&`)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is there a BOM change?"
    },
    {
      "prediction": "I don't think this should be a string, but it's not a string.",
      "reference": "It's not a good practise to delete the public static constant."
    },
    {
      "prediction": "I think this should be a better way to do this?",
      "reference": "I deleted this because `WellFormed` is immediately called by `verify.TxnPool` below. Can someone please double check this for me since it's... pretty important"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Did you actually test this with ply 3.4? That release is pretty old (2011), so I think we can bump this to at least 3.6 (2015) or even 3.10 (2017)..."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "This can be simplified somewhat to `pointer.Int32Ptr(0)`. But it is not necessary."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Clever but perhaps confusing."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "@abutcher Is it a safe assumption that secrets are the only objects that need to get attached to syncsets?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should you capture o.asflr before releasing consumer's lock?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Just asking: Should this happen, that null is passed? If this is the case I think we should think about passing an `Optional` object to the method."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "what about making a `ProfilesController` or `UserProfilesController` and having this be a `show` action instead? That would be more Railsy (although that can be considered a compliment or a dis, depending on who you are :hamburger: )"
    },
    {
      "prediction": "I don't think this is the default value for `enabled_features_found` and `enabled_features_found`?",
      "reference": "I'd move the empty assignment and non-null case into the if check directly above (adding an else clause as needed)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Please remove this extra line of whitespace"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "maybe it's time to rename `ProductSearchExportWithFilter` to something better, what do you think?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Instead of adding new code here - can you move these methods to agent_capability.go, so the same is used for unix and windows as well. this will need removal of these methods from agent_capability_unix.go as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Make it the last parameter, just in case someone uses the API with non-keyword args."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `self.enqueue(github_team, username)` and `self.enqueue(repository, username)` and `self.enqueue(github_team, username)`",
      "reference": "Don't extend an instance initialized by `Struct.new`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Just wondering - would it make more sense to simply replace `PMIX_DESTRUCT(&t->nslist)` with `PMIX_LIST_DESTRUCT(&t->nslist)` here, and then add `PMIX_RELEASE(p->jobbkt)` to the `pmix_nspace_caddy_t` destructor on line 154 of src/include/pmix_globals.c? Seems to me like we always want to have these things removed/destructed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think, we should fix/improve AbstractRuleSetFactoryTest. I guess, both apex and visualforce rules are now tested, which is unnecessary."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `callAction($method, array_values($parameters))`?",
      "reference": "In php8 named parameters were introduced and now it is required to match called method parameter name when setting parameters by array destructing or `call_user_func_array()` etc."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "easily possible to get that information without exposing internal information"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `is_pe` flag.",
      "reference": "Why do we need tristate logic (pe, foss, nil)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this change needs to be reverted to what is on `master`"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do you still need to call the superclass `createVariable` if you've already determined that the variable exists?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Ignoring the pack entry from an existing entry but using the new entry from a non-finalized index, is subtle enough that it needs explaining."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This is a revert, is it really an issue?"
    },
    {
      "prediction": "I think this is a bug in OpenTelemetry.Trace.Internal.",
      "reference": "can we delete this file altogether?"
    },
    {
      "prediction": "I think this is a bug in the unit test framework.",
      "reference": "Suggestion: log some additional info here so we know where we are i.e 'Failed to prepare coverage framework..'"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "There didn't seem to be any good place to put constants that are .NET Tracer-specific, so I created this internal static class. If there's a better place, let me know."
    },
    {
      "prediction": "I don't think this is the default value for the update device status buffer.",
      "reference": "Log message should be started with upper-case word."
    },
    {
      "prediction": "This is a hack.",
      "reference": "changes for example usage in this class"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `emby-button` and `emby-collapse` and `css!elements/emby-collapse/emby-collapse` and `css!elements/emby-collapse/emby-collapse` and `css!elements/emby-collapse/emby-collapse` and `css!elements/emby-collapse/emby-collapse` and `css!elements/emby-",
      "reference": "I know frameworks that support current directory when loading dependencies, is this a limitation of the requirejs loader or can we fix it somehow?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`ctx` is unused in EnableApplication"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "@jemc , this is one change needed in `generate_multi_dot_name`. I believe this * will do no harm to working pony code: The new code was added in a place where it is throwing an assert. So no working code will get affected. * is in sync with the rest of the method: if the parent ast node has null `data`, we are supposed to return empty string. That is possible when we have expressions wrapped in braces."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Should not be a static import."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we be using `aws.String` here? it seems there are a few other spots we could use `aws.String` in the `if change.Attachment != nil { ...` block."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `getReport` method.",
      "reference": "We can't pass raw dates like this because they need to be formatted as `YYYYMMDD` as noted in the IB. We added the `generateDateRangeArgs` utilities to handle this for us, as well as abstracting the relationship between arg name and specific dates which is not obvious just by looking at it. Let's update it to use `generateDateRangeArgs( { startDate, endDate } )` instead   Use care to make sure we're sourcing the utility from Analytics utils though since AdSense has its own version by the same name, which is different."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "`default=True` shouldn't be used for BoolParameters iirc."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It would be better to use `return refStr[12:]`. or `11`... I have problem with counting.."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Pretty sure these should only contribute to the runtime hash."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Just verifying: this change doesn't break the 18f layout, right?"
    },
    {
      "prediction": "I think this is a bug in yarpcerrors.CodeOK, but it's not an error.",
      "reference": "we should keep this counter using the \"isYarpcError\" api"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Could we just use case insensitive strings as keys instead of creating a new map implementation? e.g. simply using a treemap with a comparator `Map<String, Integer> idToPos = new TreeMap<>(String.CASE_INSENSITIVE_ORDER);` could work I think"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `GetSlot<T>` method.",
      "reference": "I think this should be a throw. Or the method should be TryGetSlot?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't usually put spaces between ( and [, and I think `path` should be passed by reference."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Make sure to `snake_case` locally scoped variable names in the future"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe we should use underscores like `health_check` - what do you think?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Do a TrimSpace before setting."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Are the fields in this struct grouped by IP address family or by function? There are separate fields for IPv4Addresses and IPv6Addresses, but a single field for DomainNameServers. Should this new field be named SubnetGatewayAddress with type array consisting of both IPv4 and IPv6 gateways?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": ".find(id) is being deprecated to Rails 5."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Will be good to have the iris interface moved to geoviews. Could this be done for 1.10.6?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "does this get wrapped in the calling method?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do we still need this test case? If your new test cases test this, then we can remove it."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `role_values_for` method.",
      "reference": "If you want to express \"any role that is not creator\" you could use the following statement: Role.where(plan: self).where(Role.not_creator_condition).any? which would be less verbose and a bit more efficient if it is used for Yes/No shared?"
    },
    {
      "prediction": "I don't think this is the case where the CA is an intermediate, so we don't want to store the root in the chain anymore.",
      "reference": "Do we need any update on the test side?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There's a few `return nil` cases above this -- we should probably move this above the big switch."
    },
    {
      "prediction": "I don't think this is an error.",
      "reference": "`lile *LeaseInLedgerError` to reduce copying?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "should it be `newsessionqueue` or `newsessionqueuer`? In case we'd like to be consistent"
    },
    {
      "prediction": "I don't think this is the right thing to do with FileAccess.ReadWrite?",
      "reference": "We don't have a requirement anywhere in Test Platform for GetStream() with write access. It is ok to directly change `return new FileStream(filePath, mode, FileAccess.Read)`."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "FWIW `from qutebrowser.browser import hints` is okay - it's just things like `from qutebrowser.browser.hints import HintManager` I try to avoid."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `get_theme_mod( 'neve_tansparent_header', false)`.",
      "reference": "@preda-bogdan let's use a filter for the header classes, something like, hfg_header_classes where we hook this logic, in neve pro"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Out of curiosity.. is there a rule to determine the package name as prevDirectory+currentDirectory."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It seems this needs to check the lazy cxt switching flag. It is used on the initial thread for early injection and in other places where the lazy switch should apply."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `isValidPropertyID` in the `validatePropertyID` function.",
      "reference": "Why not use the JSdoc annotation as it did before?"
    },
    {
      "prediction": "I don't think it's a `-ee` suffix, but it's not a `-ee` suffix, but it's a `-ee` suffix.",
      "reference": "Why don't we drop the packageImplementationVersion in general? That way the version will be fetch all that time only from the properties file and it will be consistent."
    },
    {
      "prediction": "I think this is a bug in CppGenerator.",
      "reference": "Please use the style of the rest of the code, a space between the type and `*`"
    },
    {
      "prediction": "This is a hack.",
      "reference": "nit: remove extra blank lines."
    },
    {
      "prediction": "I don't think this is the default value, but it's the default value.",
      "reference": "nit: What do you think of `copilot-task-group`?"
    },
    {
      "prediction": "I don't think this is a `eventProxyCapture` method.",
      "reference": "We should check whether or not the input node has a value since we can just have an onChange on an uncontrolled component as well."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "I think there should be some reasoning below this line about the version updating."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please use `h2o_lcstris` instead of `strncasecmp` so that the comparison would be a complete match (instead of a prefix match; current code would yield true if [val,len] is [\"O\", 1]) and that it would be locale-independent."
    },
    {
      "prediction": "I don't think this is the case where we're in minimal mode.",
      "reference": "I prefer if possible for `if`/`else` statements to have the positive case first."
    },
    {
      "prediction": "I don't think this is the right thing to do with a tuple as the second argument.",
      "reference": "Docstring would be nice"
    },
    {
      "prediction": "I don't know why this is the default, but it's not the default.",
      "reference": "Low risk to fix this by default because existing baseline consumers pass this check. We don't attempt to fix checks that have been opted out of."
    },
    {
      "prediction": "I don't think this is the case for NVIDIA architectures.",
      "reference": "What about `VOLTA72`, `TURING75`, `AMPERE80` and `AMPERE86`? We only want to set the number of teams for these two architectures or for all the architectures newer than Maxwell?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Since we have specified `load_from`, `pretrained` can be left None."
    },
    {
      "prediction": "I think this is a bug in caddy.",
      "reference": "I prefer to translate these `else if` into `switch` for more readability."
    },
    {
      "prediction": "I don't know why this is the right thing to do with `params[:state]`.",
      "reference": "This can also be a local variable in `create`."
    },
    {
      "prediction": "I think this is a bug in Gogs.",
      "reference": "Why not use `path.Join`?"
    },
    {
      "prediction": "I don't think it's a `global.googlesitekit.api` property, but it's a `global.googlesitekit.api` property.",
      "reference": "Why not `export default API` instead? This ensures we export the same that we export on the global."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is a good change I think. It greatly helps reduce name conflicts."
    },
    {
      "prediction": "I think this is a bug in JetStreamCluster.",
      "reference": "cluster not having omitempty, does this imply that cluster is required? seems empty is valid so just checking"
    },
    {
      "prediction": "I don't think this is a problem with the `MergeEnvironmentVariables` function.",
      "reference": "@aws/aws-ecs-agent, @yumex93: how concerned should we be about user provided envvar names clobbering existing envvars? i'm not convinced we should be doing additional validation here."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `Object.defineProperty` or `Object.defineProperty`?",
      "reference": "nit: aspects are defined in `OperationBase`, should `defineAspects` live there as well?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use the `create_from_config` method.",
      "reference": "Why the `os.path.abspath`? `os.path.dirname` should always give a valid directory path."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I think we should not consider special engine types on this level. I would prefer to build the specific engine path based on `application.user.engines` later on."
    },
    {
      "prediction": "I think this is the case where we need to re-check the endBound_.rel_ == RelationType::kEQRel.",
      "reference": "Is `rbegin` correct? We can't make sure that the last index column is the `rbegin` of `scanItems`."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "check it is != 0, just like `EVMNetworkID` above"
    },
    {
      "prediction": "I don't think this.droppedCount is the same as this.droppedCount.",
      "reference": "if you just do \"this.GetType().Name\" and \"this.exporter.GetType().Name\", we get what we need."
    },
    {
      "prediction": "I don't think this is the default value for the API version.",
      "reference": "That's the code that would prevent any SalesforceSDKTest from running. At class loading time, SalesforceSDKManager.getInstance() would throw a RuntimeException because init() had never been called."
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's a string, but it's not a string.",
      "reference": "there is no \"DEFAULT_REVISION\" logic, no need to define this."
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "so this is to fix a scenario where the app is first launched normally, then background and foreground through the link, we are not updating loginOption"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "It doesn't seem like the right way to implement this, because you add a new element that doesn't really exist (noteTextViewer). Instead you should modify the command handler `if (command.name === 'focusElement' && command.target === 'noteBody') {` in NoteText.jsx. Then focus either the editor or the viewer depending on what's currently visible."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We don't add blank lines in imports."
    },
    {
      "prediction": "I think this is a bug in the GNU General Public License.",
      "reference": "Please add your name to the copyright list."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "You can elide the `if` check for empty string, because if it's not a value that is set, the string will be empty anyway."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Different i18n keys. By mistake or on purpose?"
    },
    {
      "prediction": "The `ACMESelfCheckFailurePolicyRetryForever` policy will be used instead of `RetryForever`",
      "reference": "Given the description for this is `// Describes how the ACME challenge self check behaves when it fails.`, perhaps `RetryForever` is better terminology here as when the check fails, we don't just wait, we retry periodically."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: let's add a more descriptive prefix in line with the other ones? E.g. `Unable to import key` ?"
    },
    {
      "prediction": "I don't think this is the default value for `ENV['BOLT_SSH_KEY']`.",
      "reference": "This looks like it will pass an array as `:key` in the default case. That doesn't reflect how this will actually work in practice."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "Do we need this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I am a bit confused about this function. If it is used to set priority, we actually use function \"Table.BuildFlow(priority uint16)\" to set the value. If it is used to parse the priority value, I think adding a property(if you don't want to consume Match.Priority directly) to cache it and consume that property should be simpler than using string regex."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "In this case we probably meant \"package\"."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Just export `createFile` directly."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This probably needs to get shipped with plz; you shouldn't have to redefine it within the user's repo. It should use `defaultPath` like the other things up the top of the file."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "interface for bitcoin should not change if possible. i.e: networks.testnet should return networks['btc'].testnet"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "File is not `gofmt`-ed with `-s` (from `gofmt`)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "We have this functions in a couple of places. It should probably live in util or something."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "maybe this should be inside the destroy?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Do not import torch in the test function because it will import torch every test iteration and will slow down the testing speed."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I think we want to return an error here, not nil."
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure if this is the case.",
      "reference": "Nitpicking, but I think it would be more accurate to use an actually supported value, i.e. `completed`."
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `project_id` and `page` parameters.",
      "reference": "How about renaming the `ApiJob` class to `JobApi`. As per rails convention, get method is to get a single object, not a collection, can we change that to `fetch`/`where`. It would be great if we can move the `get` method to a class method."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "assignments should only be cuddled with other assignments (from `wsl`)"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "`k` is unused in PutHash"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "None of the child return null here, plus it was creating an incoherence between interfaces."
    },
    {
      "prediction": "I think this is a bug in ponyint_sched_init()",
      "reference": "Should we remove this entirely now then?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "That is way too generic a name."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "This might be overkill for test code...but as stewards of accessibility it would be appropriate to have a label in the fixture."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Are these allocations necessary, or can these be instantiated normally (i.e., `VkCommandBufferObj secondary_full_clear(...)`). If the allocations _are_ necessar, I'd vote for using something like `std::unique_ptr` and then remove the associated `delete`s."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "es.clear should call this"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "please remove. this is true by the definition of the Python language"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Hmm, I wonder if binding `<Return>` is a good idea... this means it wouldn't be passed to webpages anymore, which makes me wonder how many people rely on that... I guess trying it is the only way to find out :wink:"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Golang naming convention is to use camel case `icmpPktWithTypeCode` Often the linter will complain"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: Probably should renamed to `InitializeBody`"
    },
    {
      "prediction": "I'm not sure why this is the default value for `settings.icon` or `favicon.ico`?",
      "reference": "is `settings.icon` always null/undefined when there's no icon or does is it get set to a blank string? It might be worth wrapping it in an `isBlank()` anyway"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "put invoke to the end of the list, and other module at beginning of the list (line 86)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think that bytes is too precise. Can we just calculate the approximate value in appropriate units? Something like MB, GB depending on the value, `db capacity: 5000000 chunks (approximately 20GB)` ."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "This check shouldn't look at the content, you're already doing this with `none-empty-text`. I also think this check should be renamed to `none-empty-alt` or something like it. There is nothing specific to applets in this check to warrant putting `applet` in the check ID."
    },
    {
      "prediction": "I'm not sure why this is the right place to do this. I'm not sure if this is the right place to do this. I'm not sure if this is the right place to do this. I'm not sure if this is the right place to do this. I'm not sure if this is the right place. I'm not sure if this is the right place to do this. I'm not sure if this is the right place to do this.",
      "reference": "Why did you change the signature of this method ? You can break BC doing that"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "can you catch the error here please and return err if it can't read the template"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is this method called at another location too? I'm just asking because you didn't remove another call to `updateLibrary`"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Not necessary but you should be able to add a `?` on `is_default?` and `published?`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "here is us decoding directly the bytebuffer in benchmarks"
    },
    {
      "prediction": "I don't think this is the case where the Tracer is not initialized.",
      "reference": "When the Tracer is first created AND `DD_LOGS_INJECTION=true`, this is invoked and causes the issues described."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "NIT: If we are renaming the JsonRpcError, should we also rename this enum value to be consistent?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This could be made into a function expression, yes?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Oops, I missed this initially."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Can we add an assertion here the policy actually contains both statements created above?"
    },
    {
      "prediction": "I don't think this is the case for now, but it would be better to use the same algorithm as the bottommost level compression algorithm.",
      "reference": "a space after comma?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the current span's skew.",
      "reference": "nit formatting here and below"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think that there is a general consensus of trying to avoid this kind of mocks in the new tests that we write. I would suggest to have tests using fake service implementations. In this case, we can have a fake entry service. Examples of how tests have been written this way are the tests for the `spire-server agent` and `spire-server bundle` commands. It would be great if we can have that kind of testing here also. What do you think?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "`ctx` is unused in RunQuery"
    },
    {
      "prediction": "I don't think this is a problem. I don't think this is a problem.",
      "reference": "Couldn't we use type hints to express this?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "why you do `.classList.add()` here but `.replace()` in other places?"
    },
    {
      "prediction": "I don't think it's a teacher, but it's not a teacher, but it's not a teacher.",
      "reference": "What is this sleep here for?"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `.ht_clone_left.wtHider` instead of `.ht_clone_left.wtHider` instead of `.ht_clone_left.wtHider` instead of `.ht_clone_left.wtHider` instead of `.ht_clone_left.wtHider` instead of `.ht_clone_left.wtHider`",
      "reference": "I think that this test doesn't cover this bug correctly. When I attached the older version of the handsontable to this test it passes, should fail. Can you check that?"
    },
    {
      "prediction": "The `unflushedReady` is non-nil.",
      "reference": "Maybe this should just be passed in on construction time"
    },
    {
      "prediction": "I don't think this is the case for the multi-backend.",
      "reference": "We should create the monitor after the `if (!primary_drm)` check."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Can be removed now that slots are used"
    },
    {
      "prediction": "I'm not sure why this should be done here?",
      "reference": "The description should match the test"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "rootston needs to unset this now"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why do you rename this function?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `step_status_icon` method.",
      "reference": "since we are no longer using these numbered icons can we remove them from source control?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "both edge and normal need to set this, so set it to be default action?"
    },
    {
      "prediction": "I don't think this is a good idea to do with the `File.ReadAllText(projectJsonPath)` and `File.WriteAllText(projectJsonPath, projectJson + Environment.NewLine)` and `File.WriteAllText(projectJsonPath, projectJson + Environment.NewLine)` and `File.WriteAllText(projectJsonPath, projectJson + Environment.NewLine)`",
      "reference": "Is doing a straight string compare of the files the right way to determine this? I guess if you expect to be the only one writing this file it could work but it does seem like it might be a large string compare and if we are doing this hundreds of times that might cause some memory issues."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "What's the purpose of this change? It basically changes nothing until we want to put smth between curly braces"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Hmm, why is this needed? `wlr_input_device_destroy` should destroy the tablet tool."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "I think it's better to throw `UnsupportedOperationException`"
    },
    {
      "prediction": "I don't think this is the case for `multiple` and `multiple`",
      "reference": "`props.children` is not always guaranteed to be an array. When only one child is passed this will break. We can use `toChildArray()` to turn it into an array :tada:"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please just remove this line. We have the git history if we want the old version."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can we put some of the code on a new line to make it more readable. The max line length was 120 now, right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Remove the handling here as well."
    },
    {
      "prediction": "I'm not sure if this.queue.TryAdd(activity, maxSpinCount: 50000)",
      "reference": "Do we want to make this configurable?"
    },
    {
      "prediction": "I don't think the message is null?",
      "reference": "Prefer adding a second `positive(String, double)` that delegates down to this three-param version. Using `null` in code is generally Not A Great Idea, and it looks ugly."
    },
    {
      "prediction": "I don't think this is the right thing to do with the client_data.",
      "reference": "Is this going to break things for 18F proposals, or will these fields just be ignored?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Keys.COMMAND seems to be an alias to Keys.META. That isn't mentioned?"
    },
    {
      "prediction": "I think this should be a string, not a string.",
      "reference": "What's the reason for moving this to config from status?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't we re validate/update the in memory suppress data here?"
    },
    {
      "prediction": "I think this is the default payer, but I think it's the default payer.",
      "reference": "curious why the renumbering is required here and elsewhere?"
    },
    {
      "prediction": "I think this is a problem with the `aws.CredentialsAssumeRole` and `aws.CredentialsSecretRef.Name`?",
      "reference": "s/must specify secrets/must specify secrets or Role info/"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "let's leave this as a dev-only feature, and copy prod db to local env when needed. that keeps blazer security issues to a minimum."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We'll be renaming ActivitySampler to Sampler anyway, so this change will be non-required. Prefer to avoid changes here to avoid merge conflict with my PR doing the rename."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This applies only in the \"set\" headers case, but what about \"adding\" a header (field prefixed with `+`)?"
    },
    {
      "prediction": "I'm not sure why this is a bug in the future.",
      "reference": "I'm not sure we should deprecate this. I kinda like the idea, that we would provide all exceptions (if we throw any) with a common super type. Of course, the exception should be not a checked exception like this one, but rather a runtime exception. We maybe need additionally an internal exception that we would convert into such a public API exception. But that's out of scope of this PR - that's the question of exception handling."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You'll need to adjust the docstring :wink:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Add a TODO explaining why this is being done"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This file still uses Blockly.VariableModel..."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Small nit, in the PR description its `publicAccess` but here its `public`. Guessing the preferred naming is public?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Maybe `driver.Watcher` -> provider (2x)? This is the concrete type, this user doesn't really know anything about the driver."
    },
    {
      "prediction": "I think this should be an abstract class.",
      "reference": "can we remove this since `getDocValues` already returns an iterator? (we might need to do `T extends DocIdSetIterator` above)"
    },
    {
      "prediction": "I don't think this is a problem? I'm not sure if this is a valid encoding?",
      "reference": "Don't check this in. This is already implemented in core_extensions/ruby/string.rb"
    },
    {
      "prediction": "I'm not sure why this is a property, but it's not a property.",
      "reference": "This is used for both `id`, and `hash` we may not want these both to be enumerable."
    },
    {
      "prediction": "I'm not sure if this is a duplicate.",
      "reference": "Is this necessary? I would expect YARD to treat it as public anyway... (Don't hold off merging on this...I'm mostly just curious)."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "@wxing1292 to double check this is the right version to use?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Shouldn't there be another case for when both min and max are specified?"
    },
    {
      "prediction": "This file is part of Invenio.",
      "reference": "Don't miss this one `2: I102 copyright year is outdated, expected 2014 but got 2013`. Thanks"
    },
    {
      "prediction": "I don't think this is a bug in Cord::appendTo(std::string& str, std::string& blockPt_)",
      "reference": "the tail_ maybe nullptr?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The PR description mentions that `The controller code is extended to react to \"add\" events`, but I don't see any additional cases added here beyond the existing Create and Delete... is there something I'm missing?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it's not the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "Does it matter that #include changed to #include? ? I think the change makes sense since it aligns with the method name on Hash but unsure if anything called #include that would break with the change."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "LGTM, curious though why exactly this is in place, and are there any possible issues from not waiting long enough?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "?: is unnecessary because we already force preserve_hosts to be a string with to_s."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "should it be `newsessionqueue` or `newsessionqueuer`? In case we'd like to be consistent"
    },
    {
      "prediction": "I think this should be a `Promise` instead of `Promise.resolve`.",
      "reference": "Since lazy is re-rendered when mounting the fallback, these checks get triggered an additional time."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `isContentEditable` property, but it's not the right thing to do with the `isContentEditable` property.",
      "reference": "There is a `is_content_editable()` method just above this, what's the difference?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Hmm, I'm not sure this is exactly what we want to get across. The behavior of leaving both values unset allowing the entire config to be managed is what is indeed deprecated. It's just that not the entire field is deprecated, just that one behavior."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Given the slightly vague discussion in basename(3) about POSIX basename (modifies arg) vs GNU (doesn't), I always assumed it was advisable to pass a string copy However, I guess you'd get a \"discarding const\" warning promoted to error by our build system here if you were getting the POSIX implementation. Hah! Cool, I probably can go remove some memory copies in other parts of the code where those conditions exist."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you know somehow that this was the culprit? Even 1 minute is a lot, so I would expect the bug to lie somewhere else."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "what to do if some failed? just logging?"
    },
    {
      "prediction": "I don't think this is a big joke. I don't think it's a big joke. I don't think it's a big joke.",
      "reference": "since these thoughts are all Jack Handey's the generator should probably be called `jack_handey` to reflect that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this file is autogenerated. you should edit `model/api/api-2.json` and then go generate this file. otherwise the next people generating api.go will remove the changes you added here"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Extra empty line detected at class body beginning."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This is smart but hacky! I would probably prefer an alternate solution that would be more obvious to read/understand."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "i would not return a pointer for status here which is an int"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Those functions are not currently wrapped, so I don't think it is necessary to exclude them (at least for now)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Should we specify the name of the folder?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "it's not wrong, but you don't technical need `rdmolops` here since it's imported as part of `Chem`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think the absence of this might have been the cause of the dump file corruption. We didn't wait for the pxz command to exit, leading to a race condition between the cp and this, leading to corrupted files in some places. I came across this because the hashes created and printed were different from the hashes of the actual files in dev also."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Out of the scope."
    },
    {
      "prediction": "I'm not sure if this is a `columnSorting:eq(${columnIndex})` and `columnSorting:eq(${columnIndex})` is a `columnSorting:eq(${columnIndex})` and `columnSorting:eq(${columnIndex})` is a `columnSorting:eq(${columnIndex})` and `columnSorting:eq(${columnIndex})` is a `columnSorting:eq(${columnIndex})` and `columnSorting",
      "reference": "Maybe `sortByColumnHeader` would be more precise? The plugin has a method with the same name and it could be confusing."
    },
    {
      "prediction": "I don't think it's a `undefined` value.",
      "reference": "@developit I vaguely remember you mentioning something about some JS engines having an escape analysis feature that makes objects (and arrays?) locally declared that never leave the function essentially free from a GC perspective or something. Do you think we could benefit from that here? Or should we leave this as it is?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Remind me why this is needed?"
    },
    {
      "prediction": "I don't think this is the case for the `BooleanClause.Occur.FILTER` clause, but it's not the case for the `BooleanClause.Occur.FILTER` clause.",
      "reference": "same as above, can this be null now?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This doesn't make sense to me. Should `cv.lengths` be an integer array instead of longs? It looks like they should always be integers since the values are assigned from `ArrayData#numElements()`. That's very likely an int."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "str.Substring(3).Split(' ')[0] would also work and is more concise."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Did you mean to negate the not_a_peer check?"
    },
    {
      "prediction": "This file is not used by anyone who may have used the License.",
      "reference": "Copyright (C) 2010-2021 DBeaver Corp and others"
    },
    {
      "prediction": "I'm not sure if this is a bug in PyQt5.",
      "reference": "This seems like an unrelated change"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just to double-check -- are you sure this needs to be done *before* we create a new session? (Is `SetKeyLabel` setting what the label will be for all future keys or the label for the current key?)"
    },
    {
      "prediction": "I'm not sure why this is the default overflow policy?",
      "reference": "I thought we were removing the FAIL policy altogether...."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `--outfile` option.",
      "reference": "Could you elaborate on why you made this change?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "before the fix, does this sentence make service crash? My point is can you re-produce the problem. I'm not sure the bug is due to non-asiic code"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This comparison looks a bit strange, we should first check existence of key \"IsApiToken\" and then check if it is equal to true. ~~Besdies, s/IsApiToken/IsAuthedByToken/~~"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This might be working as is, but I'm a bit thrown by the || and then && and how things get evaluated. Testing real quick on the go playground, true || false && false seems to either evaluate the && first, or start on the right side. Anyhow could you group with braces, it looks to me like it should be ( a || b) && c in this case?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to use.",
      "reference": "add an entry in makefile to generate binary with diff name?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "hmm so we didn't validate the HTTP config for all receivers?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "ITextFormatActivity had this, can I add to have the same effect?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "not blocking: can we remove extra lines here?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "This just feels weird... can we use some kind of constant here? something like: `if (_.isUndefined(data) || data === PrivateKey.Random)`"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "if does not have a class I guess the exception should be thrown because we cannot recognize the type based on it?"
    },
    {
      "prediction": "I'm not sure if this is a field mask, but I'm not sure if this is a field mask, but I'm not sure if this is a field mask, but I'm not sure if this is a field mask.",
      "reference": "LOL: use your GitHub username?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "any tests for nextPrefix() ?"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "In general I'm saying \"if there is no common type I'm just going to skip some stuff and fail silently.\""
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "did we move the eventing logging here? Probably the eventing logging was removing and they are now using the pkg logging in eventing. If that is the case, we should do the same here"
    },
    {
      "prediction": "I don't think this is a problem with the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys defined in the core.Keys.",
      "reference": "I think that `Handler` should preserve the `operation` member and the span formatter should receive the operation name string as a parameter too, otherwise the `operation` parameter in the `NewHandler` function becomes useless if we pass a custom span formatter. Also, shouldn't it be called `spanNameFormatter`?"
    },
    {
      "prediction": "HSRPMD5 does not have a `sourceip` field.",
      "reference": "Can you merge #466? That would make the current `None` default value working and more relevant that `\"127.0.0.1\"`."
    },
    {
      "prediction": "I think this is not a valid field name, but it's not a valid field name.",
      "reference": "is reserved filed name the only possible reason this could fail?"
    },
    {
      "prediction": "I don't think this is the default, but it's not the default, but it's the default, but it's not the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's the default, but it's not the default, but it's the default, but it's not the default, but it's the default, but it's not the default, but it's the default,",
      "reference": "Would a KBFS_DISABLE_JOURNAL make more sense?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "BTW. What's the message meaning?..."
    },
    {
      "prediction": "I'm not sure if this is a test, but I'm not sure if this is a test.",
      "reference": "this should say false"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "for my understanding - are this line and the next line both necessary? they seem to contain duplicate information. same for the other test files"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "No need for the `.keys()`, iterating over a dictionary gives you its keys (and thus you can also do `key in some_dict`). With that, it also fits on one line :wink:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If we want to avoid the user calling constructor and destructor, we should add `= delete` to their declarations. If we just want to avoid writing the default behavior, we should add `= default` to the declarations. I'm more in favor of the second option to avoid an API break."
    },
    {
      "prediction": "I don't think this is a problem with the `graphene.ObjectStoreOperationResult` and `graphene.ObjectStoreOperationResult` and `graphene.ObjectStoreOperationResult` and `graphene.ObjectStoreOperationResult` and `graphene.ObjectStoreOperationResult`",
      "reference": "My preference here is to keep a stricter hierarchy. We should have a mixin or something that is an AssetEvent that Observation and Materialization can both inherit from. That way we can check the type in the frontend if we need to."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can also cast them as `set`s and compare them."
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Still TODO I guess?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Another cleanup. There are two additional `using namespace std::chrono;` under this one. Should also remove std::chrono:: from the full file. Please do this on a single commit."
    },
    {
      "prediction": "I think this should be removed in the future, but it should be removed in the future.",
      "reference": "Looking at this list of boolean flags I wonder if we should create enums for all of these options, so that the code becomes much more readable"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is this necessary?"
    },
    {
      "prediction": "I'm not sure if this is a CosmosElement, but I'm not sure if this is a CosmosElement, I'm not sure if this is a CosmosElement.",
      "reference": "How about this NS inside query NS?"
    },
    {
      "prediction": "I think this is a bug in the state manager.",
      "reference": "in line 79, sm also can be stateReader"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "maybe can not return a map directly, it will be modified by inner thread."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is the actual change here, why is this test change needed? Now the diff will send back more data?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Might be better to use a tag here. I for one have used 1000 isotopes as a tag in the past..."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "This tests seems it was broken from the start :joy:. It \"worked\" because the old sample chance was small enough that this have always be off. Thanks for fixing this. Could you also change the strings on this test? `\"Recording off\"` and `\"new span is recording events\"`"
    },
    {
      "prediction": "I don't think this is the case for the `--version` option.",
      "reference": "This is not actually the case, you need to modify `toConfiguration` below to prevent a configuration from being produced"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm worried about we hide some important log here"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "Python 3 will throw an exception for inf, but not providing a timeout will result in no timeout exception."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "As this method changes the state, it should be `POST`. Also, maybe to rename it to `createTag`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`ctx` is unused in rollbackTraffic"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Roslyn conventions have const in PascalCase."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This is not bullet proof if e.g. user has `clientPort=1234` in `zoo.cfg` and in zkHost connection string. Then we'll add a warning that dynamic config differs from zkHost, which is not entirely true since we just lack the port part. We have no way from client to read the `clientPort` from server except from connecting to the server with 4LW *ont the clientPort* which is a chicken and egg. This hack will make the comparison work for default port, which is a compromise."
    },
    {
      "prediction": "I don't think this is a bug in Datadog.Trace.Vendors.MessagePack.",
      "reference": "We can probably delete this entire file. It's not used now and we'll (probably) write a custom serializer before we ever switch to MessagePack 2.1."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `raw_ssh_args` parameter.",
      "reference": "Aren't you duplicating this option?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure we should be doing this based on the extension? Calling them `.build_defs` is just a convention"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Should remove in `_MissingPandasLikeMultiIndex:` too"
    },
    {
      "prediction": "I think this is the default value for `crossZoneLoadBalancing` and `subnets`",
      "reference": "We should scope this down to the bits that we're actually using, otherwise the API is going to be problematic, as it includes references to NAT gateways and public and/or private subnets. Copying the types to be more local to the task in hand is fine."
    },
    {
      "prediction": "I think this is the default for route53 operations, but it's not the default for route53 operations.",
      "reference": "Is it is a hard requirement for this field to be 'cn-northwest-1' when wanting to interact with AWS China? It appears that putting in 'cn-north-1' would also result in using the alternative API endpoint (with the region overridden to use 'cn-northwest-1' for the created AWS client)."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Stephen already fixed this one. Only the OverSize test is flaky now right?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `proposal_link_text` method.",
      "reference": "if the `activity_mailer` has a layout, should we include the footer in that? Realize there may also be conflicts with work @rememberlenny is working on..."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "This makes me nervous, mostly because I don't know very much about it. Will users run into the gettext error in the wild? I can't reproduce it locally, but it's hard to be 100% sure. Is disabling gettext in Pal an option?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is Java smart enough to know the generic type here? Never knew this."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "no thought given to reload"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please, don't remove the `getDisabledMetricAttributes` method. All changes must be backward-compatible."
    },
    {
      "prediction": "I think this is a problem with the `killAllSessions` command.",
      "reference": "Is this left over from debugging?"
    },
    {
      "prediction": "I'm not sure why this should be done?",
      "reference": "I've fallen for this before myself :) We _do_ call `close` inside of `done` on L65"
    },
    {
      "prediction": "I don't think this is the right thing to do with the user agent.",
      "reference": "That looks fine! You could use `\"rclone/\"+fs.Version` too if you wanted. BTW does tardigrade use http under the hood? If you were using rclone's http Client then you'd get a User-Agent and you'd also get support for `-vv --dump bodies` and other nice things."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Adding one line `prob = prob.clamp(min=EPS, max=1-EPS)` already works."
    },
    {
      "prediction": "I don't think this is a bug in the net-core, but it seems to be a bug in the net-core.",
      "reference": "another option would be to create a `CreateRequestQueue(bool lockingQeueue)`, and set it only in `InitializeTarget`, isn't? The would prefer having the creation and \"business\" rules for the creation in one region, I think `InitializeTarget` would be the best place."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Wait, I think the `subsurface_handle_place_above` code was correct before. `place_above` means \"place it above in rendering order\" right?"
    },
    {
      "prediction": "I'm not sure if this is a list.",
      "reference": "why did this change?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do you think we should have some tests here for `tlf.SingleTeam` too?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "No problem with this but might as well revert this file since nothing else changed."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "In my changes, I did not create a new `AspNetScopeManager`. I'm not familiar with it enough to know if this is a valid change or not"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Not cool with this. I think we talked about it in past. This is a side effect. If we want to introduce the side effect in our functions like `inRange` (which I am for) the side effect (error) should originate in that function and not in some internal `throwError` function. Every stacktract will start at line `2` of `trowError.js`. Been there, done that and falled back to throwing the error from the place where it should be thrown."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't need this additional method."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The purpose of this test is to ensure that the `OAuth2UserRequest` passed into `loadUser` is **not** null else throw `IllegalArgumentException`. Changing the `List` of `OAuth2UserService` mocks to `DefaultOAuth2UserService` doesn't really apply to what is being tested here. Please revert this. Thank you."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: rename to nativeStk? proto might lead to think protobuf"
    },
    {
      "prediction": "I don't think this should be a string, but it's not a string, but it's not a string.",
      "reference": "Why not `queryUUID` (and reference the same constant as in other places)?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This is also used to log, of which our convention is leading uppercase..."
    },
    {
      "prediction": "This is a hack.",
      "reference": "What about we just name it `check_exact`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "before, a binary annotation had the same service name as a regular annotation, masking the bug where we weren't querying the latter"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `has_one :trail, through: :step, as: :completeables, dependent: :destroy, as: :destroy, dependent: :destroy, as: :destroy, dependent: :destroy, as: :destroy, dependent: :destroy, as: :destroy, as: :destroy, dependent: :destroy, as: :destroy, dependent: :destroy, as: :destroy, as",
      "reference": "Where does the `7` come from?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't know how we haven't got bugs from some of these! As here this would have had a stale `value`"
    },
    {
      "prediction": "I'm not sure if it's a reserved table property.",
      "reference": "One nit here I forgot about this before but we usually structure error messages as \"Cannot X because Y. Then the recommendation goes here\" I would also recommend not using \"it\" in the message since it the pronoun is a bit ambiguous. \"to specify write sort-order\" may be clearer"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'm surprised this worked at all! It was importing the default export but `eslint-plugin-import` warned me `warning Using exported name 'initialState' as identifier for default export import/no-named-as-default`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `:teachers` and `:users` and `:teachers` and `:teachers`",
      "reference": "This was used in `app/views/video_tutorials/_video_tutorial_details.html.erb` how are we handling that now?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the following regex: `(`(, )*(?i)(request id: )(?:[-[:xdigit:]]+)`) `(`(, )*(?i)(request id: )(?:[-[:xdigit:]]+)`) `(`(, )*(?i)(request id: )(?:[-[:xdigit:]]+)`) `(`(, )*(?i)(request id: )(?:[-[:xdigit:]",
      "reference": "Is `\\S+` really the right thing? Anybody know what kind of encoding this is? Perhaps if we know it doesn't have commas, we can just use `[^,]+`. Also, parens around the comma are unnecessary, since we're not using the capture group."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This block of changes looks like you removed tests without replacing them anywhere. Did I miss something?"
    },
    {
      "prediction": "I don't think this is a hack, but it would be better to use `python::arg(\"includePrivate\")` instead of `python::arg(\"includeComputed\")` instead of `python::arg(\"includePrivate\")` instead of `python::arg(\"includeComputed\")`.",
      "reference": "n.b. private and computed values are now exposed to the API. They were hidden/not exposed before."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Nitpick: Please add a period after `link` :wink:"
    },
    {
      "prediction": "I think this is a bug in the upstream controller.",
      "reference": "we got no chance that `err` is not nil here, need to revisit how `NewUpstreamController` is defined."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Instead of building in routing for a browser-specific command, could you refactor the HttpCommandExecutor to allow arbitrary commands to be registered?"
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case, but I'm not sure why this is the case.",
      "reference": "It'd be nice to assert the right deprecation is being raised, just add a third argument of `/\"its\" method/`"
    },
    {
      "prediction": "I don't think this is the default value for this property.",
      "reference": "Do we want to add this to the docs?"
    },
    {
      "prediction": "I think this is a bug in the code.String() method.",
      "reference": "This isn't really related but makes debugging test failures much easier since you see the string representation of the code instead of the integer value."
    },
    {
      "prediction": "Should we check the size?",
      "reference": "Because of this new early exit."
    },
    {
      "prediction": "I think this is a bug in Selenium.",
      "reference": "Maybe call it `WireBridge`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "can this be removed now?"
    },
    {
      "prediction": "I don't think this is the case where the user has already created the usock and terminate abnormally.",
      "reference": "This is going to create a problem - we are already encountering issues with the length of the usock pathname on recent Linux kernels as the temp directory base has moved down to the var directory under a name created by a hash. So adding another field to it is going to add to the problem."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `AppCfnTemplateConfigurationNameFormat` for the `AppCfnTemplateNameFormat` and `AppCfnTemplateConfigurationNameFormat` for the `AppCfnTemplateConfigurationNameFormat` and `AppCfnTemplateConfigurationNameFormat` and `AppCfnTemplateConfigurationNameFormat`",
      "reference": "What do you think about moving this to the `cloudformation` pkg?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please make this private by default"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We can add `@Override` annotations to all of the implementations of this method. I think this is a best practice for us, but it would be nicer in any case."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Most of uses of `RefreshAndGet` seems to be made only for `Refresh` part, result is ignored. We can simplify this method to assigning single responsibility to it - just `Refresh()`."
    },
    {
      "prediction": "I'm not sure if optikcontainer.add_option(**args, **optdict) is a valid option.",
      "reference": "@Pierre-Sassoulas Are we sure this doesn't create problems? Without it for some reason we get an error on `accept-no-param-docs` being a duplicate error. I couldn't figure out why it did this. This solves the issue and passes the tests, but I wonder if this creates other issues.."
    },
    {
      "prediction": "I don't think this is a problem with systemd cgroup.",
      "reference": "Does it make sense to check for \"Created\" here as well? Or should it return an error in such case?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Did you mean to use `identifier.toString` here as well?"
    },
    {
      "prediction": "I'm not sure why this should be done here, but I'm not sure if this is the case.",
      "reference": "interesting! didn't realize this was needed in RSpec 3"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is to avoid circular reference"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "As the bokeh renderer also has a ``load_nb`` classmethod (and notebooks are explicitly mentioned in that method name), I would consider making ``_notebook`` into a constant ``notebook_context`` class parameter. The docstring can say it is set to True if the ``load_nb`` classmethod has been called."
    },
    {
      "prediction": "I'm not sure if this is a MongoError",
      "reference": "Where is the actual command generated here? Shouldn't this be taking in `constructor(db, collectionName, options)` and then constructing the command off of that?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Mirror the `OPTIONAL OUT` of fullpath"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please merge with master and replace with with \"future\" version."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: Change is not needed for this PR :slightly_smiling_face:"
    },
    {
      "prediction": "I'm not sure if this is a single route?",
      "reference": "if we are returning `nil` from an `else` I think we can just remove the `else` (and this method will still return `nil`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "side note: this change is ok as of today because we have not exported the results for this new type to BenchView yet. After we to that the namespace, type name and method name should not be changed (they create a benchmark ID which is used in BenchView)."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "How exactly are you expecting the user to see issues with their Midas library? It seems like all error information is being swallowed and not clearly reported to the user. Even if the eventual result is to report that loading the file failed, it seems like the exception, in this case, might have more information about why."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks good, but seems `ReadMessage` hadn't used this Deadline in Underlying `WSConnection`?"
    },
    {
      "prediction": "I don't know how to use the file name?",
      "reference": "Make it \"___*\" three underscores to make it even less likely to have a collision? I assume it will be hard to change the file name once this change is deployed..."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if we need to wait for a moment, but I'm not sure if we need to wait for a moment, but I'm not sure if we need to wait for a moment, but I'm not sure if we need to wait for a moment, but I'm not sure if we need to wait for a moment.",
      "reference": "We don't need this anymore after #2151"
    },
    {
      "prediction": "I don't think this should be a string, but I don't think it's a string.",
      "reference": "this is this removed? I don't understand in the context of this PR"
    },
    {
      "prediction": "I don't think it's a net6 object, but it's not a Net6 object, but it's not a Net6 object.",
      "reference": "`isinstance(ip6, Net6)` instead"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we really need the param here? If only partial results returned, we could return ResultCode::PARTIAL_RESULTS;"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this logic seems duplicated from the other new function. I think it should probably be a member function on `BuildTarget`"
    },
    {
      "prediction": "I think this should be the same as `b1.Path[0]` and `b1.Path[2]` and `b1.Path[11]` as `b1.Path[11]` and `b1.Path[11]` are the same as `b1.Path[0]` and `b1.Path[11]` and `b1.Path[11]`.",
      "reference": "size reduce to 1/4 of using Gob"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The Hash interface states that a call to `Write()` never returns an error. Does this also apply to the number of written bytes?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "In my tests, I found that `[[ \"\" -lt 12 ]]` evaluates to true, but `[[ -lt 12 ]]` is an error, which is why the subshell is wrapped in `\"`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I don't see a validation on `published_on`, we generally shouldn't specify it in the base factory unless the model would be invalid without the model. Is there a different way we can handle this?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the score mode?",
      "reference": "maybe add a `isExhaustive()` method on the enum to avoid these large conditions?"
    },
    {
      "prediction": "I don't think this is a hack, but it's a hack, but I'm not sure why this is a hack.",
      "reference": "so those regexps were wrong previously? e.g. they would match `/v\\/foo`? If so, raise a bug and fix on the 1.0 branch."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think with MultiBackend we could have a slightly different logic: return true if there are no configured login targets ( = getLoginDrivers returns an empty array). MultiBackend could also check all configured login targets for loginIsHidden support and verify that at least one of the configured login targets allows login, but I wouldn't go that far without a use case. In a related note, I'm not quite sure if loginIsHidden works with ChoiceAuth at all, but that's a different issue."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Should we add error info for not supporting the compressed binary?"
    },
    {
      "prediction": "I don't think this is the default value for the backoff policy.",
      "reference": "I suggest injecting this into the reconciler. For this and the others. Have Wire generate it and push it into the controller creation."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can't we just make _serializer static? We use same settings every time. I would also put those fields on top of the class for readability."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can't we just use `metadata['websocket_flow']` to identify handshake flows and not add another attribute?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `output_formatted(str)` and `output_formatted(str)` and `output_formatted(str)`",
      "reference": "Funny that we were wrapping this with string interpolation before..."
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case.",
      "reference": "I had an eslint error saying I must \"alias\" my model - so I copied this from controllers/site.js"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "unsure if the methodname can still be `GetMetricPoints()` as before..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This file contains the functional changes, the rest is for testing."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I know you didn't do this, but there's no need for the `nethttp` alias and it was confusing to me - just remove it and s/nethttp/http/ everywhere (it's fine that the package here is http itself, I do the same thing in transport/grpc)"
    },
    {
      "prediction": "I think this should be a test case.",
      "reference": "I felt that this was the most non-invasive way to fix the test, but this does expose some raw DB queries and knowledge about how SQLite works which may be a code smell. The alternative to getting this to pass is to perform enough writes to trigger a checkpoint, but that threshold is determined in the config stage and this test may not be able to know what that page threshold is set to. This could lead to inconsistent test runs which is why I elected to force the checkpoint regardless of the page threshold."
    },
    {
      "prediction": "I think this is a bug in LightGBM.",
      "reference": "Is new model format backward compatible with current v2?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `deliveries.first` instead of `deliveries.last` instead of `deliveries.first`",
      "reference": "should we perhaps write a spec that ensures we don't send a welcome email to a user on login when the user is not new?"
    },
    {
      "prediction": "I don't think this is the default value for the `AvailableLoggingDrivers` field.",
      "reference": "I think my preference would be to have the type be a `time.Duration` and use `time.ParseDuration` for parsing."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "JMX offers normal APIs for this. I don't think you want the glassfish one."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "We should really leave a TODO or something or else we will forget them ..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This exposes what a bad name `dagster_type` was, but is it crazy to want this to just be `type` -- do we gain usability by being super-explicit that this is a `runtime_type`? If so, would it make sense to rename the `config_field` to be `config_type`?"
    },
    {
      "prediction": "I don't think this is the case with the `_isSelectionAnchoredAtStart` method.",
      "reference": "It might help here if you give a brief explanation of what you mean with a selection being anchored at the start."
    },
    {
      "prediction": "I don't think this is a bug in iotex-core.",
      "reference": "move cachedStates to handle function"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't think this can just be renamed; it's saying that privacyMode is a BooleanSetting, which it's not."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "what was the reason for this change?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `System.Security.AllowPartiallyTrustedCallers` option.",
      "reference": "Minor, but these two nullable and the logic around them could be replaced by a Lazy<Bool>."
    },
    {
      "prediction": "I don't think this is the right thing to do with this, but it's not the right thing to do with it.",
      "reference": "I think I would just pass in `len(peers)`, on the principle of minimum information."
    },
    {
      "prediction": "I think this is the default value for this property, but it's the default value for this property.",
      "reference": "Spark's default value is 10 but it also rewrites IN as OR/EQUALS. We can do better that this because of the way we evaluate IN predicates. On datasets we tested this, we saw performance improvements on IN predicates with up to 200 elements (on sorted column). We may increase the default value a bit but I am very reluctant to make it more than 300 since our jobs were 20% slower with IN predicates that contained 300 elements. That being said, the optimal value still depends on a particular query and table."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Please update copyright year."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Same here, could just be `std::setprecision`."
    },
    {
      "prediction": "I think this is a hack, but I don't think it's a good idea.",
      "reference": "Do we still want the \"admins\" gate?"
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "Simple Storage **Service**"
    },
    {
      "prediction": "I think this option is disabled.",
      "reference": "nit: `it is assumed`"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I would appreciate it if you could refrain from using `stdbool.h`. We allow the header files of H2O to be included from C++ (which means that `bool` might be a C++ type), and therefore my preference is to not use `bool` in our code (but instead use `int` or `char` for the purpose) to avoid confusion."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@danielbidala What happens if `searchScope` is not defined in `config_relation.yaml` ?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Do we want maybe a 1min timeout?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I guess code never reaches this line, you can remove `else` block and just `return a[0], a[1]`. Also, probably rename `a` to `auth` as well."
    },
    {
      "prediction": "I'm not sure if this is a Map<Integer, ByteBuffer>, but I'm not sure if this is a Map<Integer, ByteBuffer>, I'm not sure if this is a Map<Integer, ByteBuffer>, I'm not sure if this is a Map<Integer, ByteBuffer>, I'm not sure if this is a Map<Integer, ByteBuffer>, I'm not sure if this is a Map<Integer, ByteBuffer>, I'm not sure if this is a Map<Integer, ByteBuffer>",
      "reference": "Doesn't this no-arg constructor need to be public for serialization to work?"
    },
    {
      "prediction": "Hierdie veld moet \\'n datum gelyk of voor :date wees.',",
      "reference": "Just use the word \"veld\" instead of \"gebied\" here"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "This change (import org.shredzone.flatter4j.model.User;) does not seem relevant to this fix / commit."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should be a Bool() rather than a String(). (See the other PR for an example)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should be a failure if we don't get the exact number of expected rules. You can use a constant if you don't want to update several lines any time you update the test rule strings."
    },
    {
      "prediction": "This is a hack.",
      "reference": "We need to switch from BeamSync to FullSync when we download all the needed headers, blocks, receipts and state"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why you duplicate it? The underlaying transport should live as long as the multiplexed one. And must be destroyed after protocol is destroyed. Duplicating the transport may lead to object references hold and maybe memory freeing problems. I think this property must hold a reference to it and not a copy. The copy can lead to memory freeing problems."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`in.Status.Experiment.Phase`. we can omit `ChaosStatus`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Just curious... why the alias here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Seems like this should conflict with changes I made during merging of the 20.2 RESX file translation"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Why disable this rule?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `self._proc.start` and `self._proc.stop()`.",
      "reference": "I think you don't need the `... if '{}' in arg else arg` part - if the arg doesn't contain `{}`, `arg.replace('{}', ...)` will return the unchanged string anyways."
    },
    {
      "prediction": "I don't know how to use `log_util.get_logger(__name__)` instead of `log_util.get_logger(__name__)` instead of `log_util.get_logger(__name__)` and `log_util.get_logger(__name__)` instead of `log_util.get_logger(__name__)`",
      "reference": "nit: Should we make this an attribute of the LoadGroupMembersPIpeline class?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "need to update this command to use the name field instead of principal_id"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: I can't help but think the privateTransactionHandler should be a base-class member ... every Priv Json RPC seems to need it..."
    },
    {
      "prediction": "Honeycomb needs this flag to be set to true.",
      "reference": "Why does this start the main activity and not the preferences? With `overridePendingTransition(0, 0)`, this could instantly switch the theme without the user being disrupted"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Prefer a human-readable string rather than querying specific technologies. How would I indicate a session is running on BrowserStack? Or some custom thing?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It appears as though whoever checked in python changes didn't re-run regenerate:expected. I am modifying these files as a result of running that after a sync and build."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was copied from JavaMethodViewGenerator; only the `public static` method modifiers were added."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this is going to throw for frontier transactions post-london"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "The catch clause is not needed. The finally clause alone is enough."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Prefer a human-readable string rather than querying specific technologies. How would I indicate a session is running on BrowserStack? Or some custom thing?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Changing the default value for isClosed from TRUE to FALSE can have other repercussions. We might miss throwing error. Can you please confirm this change."
    },
    {
      "prediction": "I don't think why this is the case.",
      "reference": "Please use more meaningful names than `te`here and in other places."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Perhaps this would be more idiomatic as `ConfigFor(interface{}) (*PluginConfig, bool)`?"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "nit: We could import `APPLICATION_AMZ_JSON_1_1` from `constants.py` here."
    },
    {
      "prediction": "I'm not sure if this file is in the project root.",
      "reference": "Should this not inherit from IMvxMainThreadDispatcher?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "line is 167 characters (from `lll`)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: consider adding a blank line between L15 and L16."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is another bug fix: Without skipping the bytes of the vector this would read garbage data."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why need this? i don't see Gen.CreatorPubKey being used?"
    },
    {
      "prediction": "I don't think this is the case for the `/history/feed` and `/history/comments/feed` and `/history/comments/feed` as `:as => :changesets_comments_feed`",
      "reference": "As previously mentioned, best to drop this locale override. It's not something we only provide in exceptional circumstances. Moreover, it doesn't work for this PR anyway, while massively increasing the code complexity!"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "is this supposed to be `Desired`?"
    },
    {
      "prediction": "I think this should be a test case.",
      "reference": "The iterator is not wrapped when the score mode is set to `COMPLETE_NO_SCORES` so you don't need to change this assertion anymore ?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `os.makedirs(folder)` and `os.makedirs(folder)`.",
      "reference": "Is there too much spaces there? (should be 4 I think)"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "IS_FIRST_PULL revision is better to use instance property, not static. When KieClient has only one instance, instance property is better. When KieClient has many instances(not possible), static is not good eitheir."
    },
    {
      "prediction": "I don't know how to use `fontawesome5_icon_mixin`?",
      "reference": "This needs to be removed since we removed the mixin."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can `weight_` be deleted?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is fine, but by Symfony convention this part is responsability of the compiler pass class, i.e `DependencyInjection\\Compiler\\?`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `puppet master --configprint user` and `puppet master --configprint user` and `puppet master --configprint user` and `puppet master --configprint user`",
      "reference": "The host object already has a nice way of querying configprint. Try `puppet('master')['user']`"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Let's call this `share` and not `upload` - the user wants to share their flows, uploading is just the implementation of that. :)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It would be better to keep focus on the main text control. But to get around the fact that Dialogs focus their first child on show, even when not active, something like Dialog.isActive should be chcked when appending text, rather than whether the text control has focus."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So is this invoked every time we extend the trace?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Why not use switch here?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I think `NoAuth` is a better name"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This does create a minor bifurcation in how closing the InputWriter is done in success vs failure cases. Is there anyway to merge this with the success exit path? This is something that seems like it would be better as a function closure instead of method on the `$esapi.Name` type. Can the `es.Close` not be used instead of this method?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please keep this blank line. PEP8 says: > Method definitions inside a class are surrounded by a single blank line."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `per_page` parameter.",
      "reference": "You are not passing in a `:params` key here."
    },
    {
      "prediction": "I think this is a bug in the hcsshim.GetHNSNetworkByName function.",
      "reference": "Probably change \"ovs\" to \"OVS\"."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Please linebreak this"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`= default` is implied here, so having it is redundant. Is it a stylistic choice to include it, or just an oversight?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe it's time to fix the param name for this interface?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why are we removing it? Looks like useful info. Obviously, field names should change."
    },
    {
      "prediction": "I think this is the default value formatter.",
      "reference": "Missing fallback to MessageTemplates.ValueFormatter.Instance"
    },
    {
      "prediction": "This is a hack.",
      "reference": "The parameter in the docstring should be fixed too. Actually, why don't you try to implement the other axis? It wouldn't be impossible to do if we use pandas UDF from a cursory look. We have enough time before the next release currently."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `gapi-cloud-osconfig-go/google.golang.org/genproto/googleapis/cloud/osconfig/v1alpha1` or `gapi-cloud-osconfig-go/google.golang.org/genproto/googleapis/cloud/osconfig/v1alpha1`?",
      "reference": "This also runs a patch if its in the middle of one."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we rename this method to `updateKnownStatus` ?"
    },
    {
      "prediction": "I don't think this is the case where the origin tag is set to the root span.",
      "reference": "Maybe it would make sense to move that to DecorateRootSpan? Currently it only has Azure stuff, but given the name of the method I feel like it would be semantically appropriate"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with it.",
      "reference": "nit: these imports were in a separate group to ones from this repo"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `isPushMethodEnabled(String dispatchMethod)` method.",
      "reference": "Is it possible to rename the methods to `isXXXMethod` to keep the usage by the caller generic? The caller could use the result of these methods to verify whether a feature is enabled or to validate an input value for example."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `rimraf`?",
      "reference": "Don't penalize everyone with 250ms delay b/c some machines have problems."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "This try-catch should be here so that watcher thread doesn't just exit in case of an exception. This change alone would probably be enough to fix the error as well, assuming that there's another `ENTRY_MODIFY` event when the file write is finalized. But of course not a perfect fix because it doesn't protect against possibly reading a non-empty but only partially written file?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Weird that we have to check for `s == nil` here.. I would instead have fixed the call stack to find out when this gets invoked with a nil server."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `Ember.Handlebars.Utils.escapeExpression(erroredEmails.join(', '))` and `Ember.Handlebars.Utils.escapeExpression(erroredEmails.join(', ')`)` and `Ember.Handlebars.Utils.escapeExpression(erroredEmails.join(', ')`)` and `Ember.Handlebars.Utils.escapeExpression(erroredEmails.join",
      "reference": "The `import` statement for `Ember` is missing in this file."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Awesome :tada: I'd love to have a test case for this so that we don't regress on this feature in any future refactorings :+1:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For testing some of the rounding functions"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `currencyDataFactory` and `currencyDataFactory` and `currencyDataFactory`?",
      "reference": "This should be present in UPGRADE notes. Also on currently running projects you should suggest users to update these settings."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Are you sure you want to do this? This will affect the working set block cache too, such that it'll now be tracking global free space. It throws off the fraction calculation."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why would the read access need to be mutexed? The caller might still get a wrong answer since the value might change immediately after the mutex is unlocked before the caller receives the value."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This fits on one line without the parentheses :wink:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like `TestCloudRecovery` changes are unrelated?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Try to separate it to different methods. Invoke is huge :)"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Looks like another spot that would benefit from `truncate`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This change is not related to what this PR wanted to fix, but undefined behavior sanitizer warns without this parenthesis because `h2o__tokens + i` overflows."
    },
    {
      "prediction": "I'm not sure if this is the case for the `no-docstring-rgx` config option, but it's not the case for the `no-docstring-rgx` config option.",
      "reference": "This is actually incorrect and should be the other way around. Going to fix this tomorrow. If `no_docstring_rgx == re.compile(\"\")` no function should be checked, since every function matches the pattern. If `no_docstring_rgx == re.compile(\"^$\")` all functions should be checked."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Should this be in a config file?"
    },
    {
      "prediction": "I'm not sure why this should be a function, but it's not a function.",
      "reference": "purely preference, but have you considered using parentheses to indicate that a method is being tested? e.g., `describe('eachAsync()')`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not return success?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please use snake_case for properties to keep it consistent with the rest of the codebase."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i don't understand why we need this change. what information is this providing when running in less than Debug loglevel? I prefer to revert this"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Oh, so this test leaks DateTimeUtils offset? It would be safer to place the reset in an `@After` method to not cause side effects even if the test case fails."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `googlesitekit-idea-hub__footer` class.",
      "reference": "Kind of a nit-pick, but is there no way to solve this while still not rendering an empty div if `footerText` is empty? We could still use the `Row` to maintain the same layout but then only render the `Cell` for the pagination - I think it's possible to use specific classes to horizontally offset?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Template is also not an object type so I don't expect to notify on templates. Instead when applying templates, we'll be updating roles/policies/services/groups."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Had to fix this to get my tests passing (should have been a new PR sorry)."
    },
    {
      "prediction": "This is a hack to make it easier to test if the server is using HTTPS protocol.",
      "reference": "Small nit, and sorry for not spotting sooner.. this should have `omitempty` on it, else when marshalling nil values into json, it will be `caBundle: null` which trips up some JSON parsers"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `transpose` parameter.",
      "reference": "Would be good to say the normal behavior is scanline order (left to right, top to bottom) and that transposing makes it work top to bottom and left to right."
    },
    {
      "prediction": "You can also set the `--drive-use-created-date` flag to true.",
      "reference": "Perhaps note here that `--drive-use-created-date` takes precedence if both set?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Use EPS=1e-15 as that in atss_head or FCOS head."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is there a need to replace the Index with a MasterIndex?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "are we adding stop state change in a different PR?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "How much difference is there between sort and sort_by ?"
    },
    {
      "prediction": "I don't think it's a bug in this code.",
      "reference": "count doesn't seem to be used. Let's remove it."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Mongo is a hard dependency for Mongoid. Why do we need an if-statement to if it's defined? We should always use Mongo::QueryCache"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Does this point out at a ROR funder id? If so, could we get rid of the `funder_name` field on the plan and just use the `name` of the funder with id `funder_id`?"
    },
    {
      "prediction": "I think this is a test for the `FB_TS_TEST` environment variable.",
      "reference": "Use !! to cast to bool, rather than the ternary bool antipattern."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why is it in the list twice to begin with?"
    },
    {
      "prediction": "I don't know why this is the case for the `pzLocked` flag.",
      "reference": "This way you will **never** be kicked while monsters are around you."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Can you please revert changes to files in the `thoughtworks` package? This is legacy code and we will eventually phase out RC."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `moduleSlugs` and `moduleSlugs`?",
      "reference": "This just fixes an unrelated prop type error, correct?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was a bug in KBFS-2071 -- oops."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "// Condition is a condition for ... Condition"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Might be good to test that no emails were sent out, either. You should be able to use `deliveries` for this"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Right now this is experimental and deeply flaky. We left this at `info` to make debugging user reports a lot easier."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Is this new list being consumed yet?"
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "moved to `errors.go` which is the only places `math/rand` is used in this package"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This use is wrong, corrent is: `Shopsys\\FrameworkBundle\\Component\\Environment` It is the same in classes below"
    },
    {
      "prediction": "I don't think it's a valid host, but I'm not sure if it's a valid host.",
      "reference": "This is not really needed, the line added in `GridNodeConfiguration.java` is what really fixes the `remoteHost` regression."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "For my understanding, why was this removed?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "the whole idea was to display information on the plugin directory in case it was missing - need to add if...else... and display the plugin dir if it is configured (non empty) but cannot be found"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can you please set this as an error on the password view, rather than a toast, just to make sure that it is kept consistent. Check out a couple of lines below."
    },
    {
      "prediction": "I think this is a bug in tequilapi_client.Client.",
      "reference": "Shouldn't we pass here a proposal too?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "im not a huge fan of exact text match in these tests, not sure what a good solution is that solves the same problem"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "this should _not_ be in the api. all postage APIs have moved to the debugAPI"
    },
    {
      "prediction": "I think this is a hack, but it seems that the `file` key does not exist in the `file` key.",
      "reference": "Including both functions seems like overkill for this PR since only _is_internal_node is ever used. Keep them if you think they'll both be used in the future, but if not, the code will be easier to read if you collapse the logic into a single function."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "It seems that the two words mean the same thing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need to set lastLogTerm_ to committedLogTerm when `lastLogId_ < committedLogId_`, on line 286"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "About ~7% memory usage increase on average, at most 512KB"
    },
    {
      "prediction": "I think this should not be used in the Handle interface.",
      "reference": "Was this too big of a pain to do now?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why need to spend time for initializing of array? when will we rewrite the contents anyway? This can take a lot of time in some algorithms. Especially if the filling is in sequential mode."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Can this be `null:false, default: ''` to avoid the nil vs blank issue?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `sshd_config` command, but it seems that the `sshd_config` command does not support --stdin`.",
      "reference": "Had to add this to get macOS to work."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "What is the usage of this class?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we keep the original signatures as well, so we do not have to rewrite the method calls everywhere and add `null, null`? I think this could greatly reduce the changes needed in this patch"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Ideally this error should not be swallowed (can do in the next PR)"
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "Wait a minute... You're passing it as a POST parameter. There's no way that can work."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "minor: to be consistent with other logs, either use \"cleaning up\" (preferred) or \"cleanup\"."
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "Adding the config changes to the consul config template `consul_config.py.ctmpl` would be helpful too."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "While we're at it should we add Department? See Dataverse Category: Add Department #2829"
    },
    {
      "prediction": "I don't know why this is the right thing to do.",
      "reference": "Files should have an extra line at the end of them."
    },
    {
      "prediction": "I think this is a hack, but it's a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "TODO: check whether this is needed or not"
    },
    {
      "prediction": "I don't think this is the default value of `IsInsecure`?",
      "reference": "`ReadConfig` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is duplicated with `+build !cgo`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `implicit_wait` option.",
      "reference": "This should just be `.not_to raise_error` otherwise it potentially hides errors"
    },
    {
      "prediction": "I don't think this is the right thing to do with a function that takes a Column and its DataType and returns a Column.",
      "reference": "Line 175 needs to be indented so that it's under `sfun`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It looks strange a bit. What is the reason?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is this one of those `LexicalPreservingPrinter` issues?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we also add the length of the slice here? Some like `<binary> len %d`"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "move this line together to after line 16, group internal packages together"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "How about using a reference(project_id) instead of project name"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "File is not `gofmt`-ed with `-s`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "@qqmyers this looks fine but have you seen any performance issue here? If so, we could right some helper method like doesExternalToolNeedDataset(externalTool). But if there's trivial performance impact, not worth it."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Make this a member variable instead (move to header inside `class` and rename to `m_bUsingLocalPrefs`)."
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function, but it's not a function.",
      "reference": "Generally I'd say we should factor this out into something more extensible (check an array of potentially skipped tests, for examples), but since we're likely to remove this soon for scheduled work I think this is fine. What do you think @daprahamian?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why are we skipping these tests? they should be passing in HIP-Clang."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think a \"string\" in Scapy's spirit (if such a thing exists) is actually a `bytes` object in Python 3 (see `Str*Field`s). So maybe `RandString._fix()` should return a `bytes` object. What do you think?"
    },
    {
      "prediction": "I'm not sure if this is a JSDOM module.",
      "reference": "This can be combined to 1 line, just tested, seems to work."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `isQuorum` flag set to true.",
      "reference": "what needs to happen if it is not present?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`DeploymentConfig` is only for deployment configuration not Piped configuration so `ds.DeploymentConfig.PipedSpec` is always nil. Instead of that, you can have Piped config with `e.PipedConfig` because it is placing inside `executor.Input`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `s3.s3_set_bucket_object_acls.rb` command.",
      "reference": "Simple Storage **Service**"
    },
    {
      "prediction": "I think this should be a function, but it's not a function.",
      "reference": "This line doesn't seem to be right?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "this need to be moved up after getting policy.."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I'm curious - is there a way to test these?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This was broken before as the name of the metadata table started with its type, not catalog."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe remake `VersionAsString()` function, so that that we would have build info in all places"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This should probably say something other than SSL_peek?"
    },
    {
      "prediction": "I think this is a bug in the License, Version 2.0 (the \"License\");",
      "reference": "Nitpicking, but this should be capitalized since it's a product name :)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Why do we need RawTransactions?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "File is not `gofmt`-ed with `-s` (from `gofmt`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should not be this lessThan15MinAgo ?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Would it work if we changed the return type of 'RejectRequest*' methods to Exception and instead did `throw RejectRequest(...` ?"
    },
    {
      "prediction": "I think this is a bug in Tizen 4.0.",
      "reference": "It is not a \"perfect\" test, but: webOS 1.2 emulator says `probably`. webOS 3 emulator says \\``. webOS 4 emulator says \\``. Why did you remove `options.supportsDts`?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This check should be after the HIP_INIT_API to ensure HIP tracing & lazy init works correctly. Also return should be wrapped in ihipLogStatus() so that logging works correctly."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can't use short array syntax for the 3.1 release branch."
    },
    {
      "prediction": "This is a hack.",
      "reference": "@rhc54 Is this intentional or for debug purposes?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to do with statsd.",
      "reference": "Maybe it should be `plugins.history` here instead of `listeners.X`, since we use those for listeners configured via `.ini` files?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Hmm, I also don't have a better idea here. As a small thing, could you make this `@team_page.present?` or similar to make the intent slightly more clear?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Without that check it would fail later (probably in the getDecryptingCipher method) but the error could be hard to make sense of."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't think that this belongs in the host code. A host is pretty much unaware of what hypervisor is running it and I don't want them to be so coupled to their hypervisor."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I'm here to tell you that this doesn't make sense because of the way it works. `setuptools.setup()` installs this only for setup-time and then discards those. But the problem is that it will not pick up a newer version because the older version is already in runtime and module cannot substitute itself. The proper place for adding build deps nowadays is `pyproject.toml`->`[build-system]`->`requires'."
    },
    {
      "prediction": "I don't think this is a bug in the testify.js.",
      "reference": "fakeConnectionManager -> mockConnectionManager. We probably should not use the `fake` anymore."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Code style. Btw, it's weird Codacy didn't catch that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "no need in BigInt just m.Unwrap().Big().Bitlen() == 0"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I assume you want to change NetworkPolicy to use bundles in a separate PR later?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: We could parameterize the commit hash, as it's used in multiple places."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "move this above the \"Constants\" as this is 3rd party ones"
    },
    {
      "prediction": "This is a hack.",
      "reference": "`assert not in`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "just curious, why was this modified?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm curious why the table name is bound at compile time? Is it just to save the table create/drop overhead in a prepare-once-execute-many situation?"
    },
    {
      "prediction": "I don't think this is the right thing to do?",
      "reference": "quick question, isn't ProcessJob used by all job types? Then why is JOB_ID not found?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "looks like you forgot to actually increase the version"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `RecordHttpServerAttributes` method.",
      "reference": "I think it might be helpful if we add `Default value: False.` on the end of the summary."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I think the check should be `config.sync.fullSynchronization === false` - otherwise this will get triggered even when full sync is `true`."
    },
    {
      "prediction": "I don't think this is a problem with the `SealedSecretEncryption` in the `SealedSecretEncryption` section.",
      "reference": "this blown my mind  "
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "this should be controller-container-status"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "Sort import. You can use IDE's organize import feature."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Can you please revert changes to files in the `thoughtworks` package? This is legacy code and we will eventually phase out RC."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This PR is off to a rough start. :)"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Actually, it looks like the entire `normalizeProxyConfiguration` function isn't needed anymore"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "How about `unless current_path == carts_path`?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "You need to modify the copyrite aliases so it's done automatically."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Quick question: Is this true for all `onAnimation*` and all `onTransition*` events?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string.",
      "reference": "Should sending an address into address error? Since the call isn't needed, and could be fixed easily."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This is the wrong MDC; see MDCLoggingContext which imports `org.slf4j.MDC`"
    },
    {
      "prediction": "I'm not sure if this is a database-specific query.",
      "reference": "Maybe we can clarify a bit what that means."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This entire method can be deleted; it isn't used and it isn't an override of Stream."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "We avoid static method imports. Can you call `MetadataTableUtils.createMetadataTableInstance` instead?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "No need for this, as pylint already only turns things off for this function and it's needed for the entire function."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `include_mentor?`?",
      "reference": "I'm actually surprised this is valid Ruby. I thought you'd need either `delegate(...)` or `delegate \\ ...`."
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Why change this?"
    },
    {
      "prediction": "I don\u2019t think this.opts.bundle is set to true.",
      "reference": "Maybe change it to `'Can't UPLOAD remote files when bundle: true is set'`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need to drop the remaining items from the batch? Otherwise we might end up with a dead loop. Add @CodeBlanch for awareness."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Because power is now added during `submitPoSt` this is needed for setting power in the genesis block. Again let me know if this bootstrapping solution is flawed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "To be consistent, these should go at the top between `DateTimeZone::listIdentifiers` and `SQLite3::createFunction`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think we should avoid changing any lucene classes for the moment - fileModified() can probably stay where it is?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "GONE breaks formating of \":\". or is it fixed below?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What do you mean with this? Won't the deprecation be inherited?"
    },
    {
      "prediction": "I think this is a bug in C++.",
      "reference": "line between \" and \" should be <80 chars."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "What will happen if neither `rvm` nor `ruby` is present in the .travis.yml?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `len` parameter.",
      "reference": "@p-l- Hey it seems that this was len-4 ?!"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack.",
      "reference": "This is something I added which resolved a few large errors in the output, although not related to the refactor here I don't think."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "i have removed this line because whenever a video is played in AntennaPod this line was making play button invisible"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to do this. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "remove temporary code"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "* Should be tagged `@Unstable` * Should be a default method, returning `null` * Also, perhaps `Optional<Long>` instead of just `Long`? Always empty when the BASEFEE isn't relevant? If so the default is `Optional.empty()`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Minor detail, but let's use the interpolated template string syntax instead."
    },
    {
      "prediction": "I think this is the default value for \"CLOCK_REALTIME\", \"CLOCK_MONOTONIC\",\"CLOCK_PROCESS_CPUTIME_ID\",\"CLOCK_THREAD_CPUTIME_ID\",\"CLOCK_MONOTONIC_RAW\",\"CLOCK_REALTIME_COARSE\",\"CLOCK_REALTIME_ALARM\",\"CLOCK_BOOTTIME_ALARM\",\"CLOCK_REALTIME_ALARM\",\"CLOCK_",
      "reference": "this line is so long, split it to multi lines."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Looks like this might be one of those \"promoted features\" where you can enable it by _either_ enabling the extension _or_ enabling the feature bit. If that is the case, I think this needs to be: `(device_extensions.vk_ext_scalar_block_layout == kEnabledByCreateinfo) || (enabled_features.core12.scalarBlockLayout == VK_TRUE)`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `__APPLE__` variable.",
      "reference": "Why should we define it for v1? This is preserved only for backward compatibility, all further modifications must be done in the latest vX"
    },
    {
      "prediction": "This is a hack.",
      "reference": "This is a definite improvement! Hardcoding nonzero is vastly better than hardcoding length. Even so, is there no way to determine the actual value of nonzero in a way that doesn't load the entire dataset?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "do we have a way to avoid the string concats, if there is no username/password in the Uri? if (uri has UsernameInfo) { do what is done in this PR. } else { existing behavior. }"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "do not print the payload since it might be corrupted, you can get the data with _debug.http.response_payload configuration property"
    },
    {
      "prediction": "I think this should be an existing file?",
      "reference": "maybe \"app init creates an copilot directory and a workspace file\"? since you validate for the file as well."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `has_many :trails` option.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Nit: Could rename this file from SabreEvent.php now that it's not for Sabre"
    },
    {
      "prediction": "This is a hack.",
      "reference": "I believe this `Stop` function _is_ called with deferred."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This entire clause should now be removed. It was only relevant if `accountID` couldn't be parsed from `clientID`, which is now no longer needed."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "FTR: Unlike commonly known practice, `latest` in Ansible docs corresponds to the stable version, not to the latest state of the main Git branch. Is this your intention? Just checking..."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Why do we have || CharInfo::UnknownCharSet here? I do not see it it in neighbouring statements. This is just for my understanding."
    },
    {
      "prediction": "This is a hack.",
      "reference": "isn't `HttpWebRequest` an expensive key value?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `where` statement.",
      "reference": "couldn't we run this query whether there are observations or not?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This shouldn't be needed to change right?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This seemed broken to me. Why would browserify only check the (previously `cdn`, now) `bundle` example? And even so, the path is incorrect here. Fixing this is unrelated so should not go into this PR I feel. But when we fix this in master, perhaps that solves the reload issues that you experienced @hedgerh?"
    },
    {
      "prediction": "I'm not sure if this is a bug in ddwaf library.",
      "reference": "Same question, do we have potential version-conflict crashing scenarios here?"
    },
    {
      "prediction": "I don't think this is the case, but it's not a good idea.",
      "reference": "Definitely not required, but it would be better if you had a constexpr for `\"INPUT_DUMMY\"`"
    },
    {
      "prediction": "I don't think it's a problem here. I don't think it's a problem here.",
      "reference": "It seems ok. Because already created a file name at line 1815 and already checked if it is null or empty at line 1816. If file name is null, then already this line will not executed."
    },
    {
      "prediction": "I think this is a bit of a hack, but I don't think it's a bit of a hack.",
      "reference": "Can all the BaseFeePerGas methods that are added be removed? It's not needed for the bomb and not referenced anywhere else in this PR."
    },
    {
      "prediction": "I think this is a bug in cobra.",
      "reference": "util.Warning()? Easier to say."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "these 2 no longer needed after refactor"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "most spec options appear to be snake case - `fa_direct_raw_block`, let's stick to that convention"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Looks like we can then drop this dependency."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "3) Subscribe to the script change signal in `FlowMaster.__init__`. The event handler should call `self.masterq.put((\"script_change\", script))`. 4) Add a `handle_script_change` function, that once called, takes the script object and calls `script.reload()`."
    },
    {
      "prediction": "I'm not sure why this is a string, but I'm not sure why this is a string, but I'm not sure why this is a string.",
      "reference": "This method is for unit testing only, right? How about making it package private? This way the readers would know that this is not a public API outside this package and would reduce the search space."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "accidental? i guess it's the same as any other boilerplate"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "shadowing the builtin, let's use function or func or callable_"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `list.__hash__` for the `Unhashable` class.",
      "reference": "Can you add some good examples, for instance integers, strings and whatnot?"
    },
    {
      "prediction": "I don't know if the License is available.",
      "reference": "Can we just have 2017 here @kmova if possible, as i seen in other projects as well( kubernetes etc..), they mentioned only the year when the file has been created."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@Tony-LunarG I just realized that this differs from the previous behavior in that spirv-opt will run on the byte code if there are any \"group decorations.\" If this is a problem, I can add an additional constructor to keep the pre-existing behavior."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Nit: continuation lines should be indented 4 spaces from the start of the statement."
    },
    {
      "prediction": "I don't think this is a bug in sysfs_region_destroy, but it's a bug in sysfs_region_destroy, but it's a bug in sysfs_region_destroy, but it's a bug in sysfs_region_destroy, but it's a bug in sysfs_region_destroy, but it's a bug in sysfs_region_destroy.",
      "reference": "Are these protected by any kind of lock?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `firewall_rule_create_time` and `firewall_rule_hierarchical_name` and `firewall_rule_hierarchical_name`",
      "reference": "This should probably default to a string, as get_resource_ancestors is causing the tests to fail due to the rsplit on a None hierarchical_name."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I prefer not to have markdown here, while it is nice for the site this is also shown for `kubectl explain` where this will look weird"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "@durran Was this change intended to be included in this PR?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Feels like this could have a default null value to remove the need for this explicit \"null\" use."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "\"failed to create ...\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "No formatting directives, `glog.Error` will do just fine."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `implicit_wait` option.",
      "reference": "This should just be `.not_to raise_error` otherwise it potentially hides errors"
    },
    {
      "prediction": "I think this should be done in the future.",
      "reference": "Need an `if err == nil {break}` above this line so that we don't log/sleep if the retry succeeds."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Separate it to different methods :D Invoke method look's like old fashion portal class :D"
    },
    {
      "prediction": "I think this is a hack, but it's a hack, but it's a hack.",
      "reference": "Collapse/expand animation of filter is broken - not smooth."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "so during the `script` stage we run `mvn install`?"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core.",
      "reference": "we may need to move CandidateNamespace to this protocol as it is only used here."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "Just to confirm, this will take care of all the nodes in graph. right?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "nit: remove this line. All \"arrange\" may be in one code block."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This name is not a good fit, what about `ExtendedAttribute`? Or even just `Attribute`?"
    },
    {
      "prediction": "I think this should be a test, but it's not a test.",
      "reference": "lets keep our \"testing framework\" header only if possible. since there is an `assert(0)` in there, it is intended to halt on the first test failure."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "I was saving this white-space for my retirement :nit:"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "What if you don't want to continue with the behavior, but you just want the deprecation to go away? Should we add `skip_after_action :discard_flash_if_xhr`?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "change `accountNonceMap` to map[address.Address][]uint64"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The `CLIENT_CONFIG` is \"client_config\" with underscore, so we can't reuse it in the second arg."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Does this mean all admins get the default batch size (which is 20) no matter the value of `-sync-batch-size`? It seems the command line flag doesn't do anything then does it?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Set default value as empty array instead of null"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would be good to UT this case"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this was updated after linking the latest ethereum/tests after a submodules recursive update"
    },
    {
      "prediction": "I'm not sure if this is a component.",
      "reference": "Todo: find a way to only do this in one spot, ideally with defaults for the stuff we use"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Imports should not have blank lines. Sorry there isn't a checkstyle rule running for this yet, we still need to update the build for this one."
    },
    {
      "prediction": "I'm not sure if feval is a callable.",
      "reference": "Please move this to L3115 to group the code logically - all code for `feval` in one place."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This was done to wrap the operation so it could be spied upon during testing. Likely needs to be undone once an alternative test is discovered."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I feel we need to impose a lower limit here maybe? What about a max and default for when none is set?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "ineffectual assignment to `err` (from `ineffassign`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Ahhh... this makes sense. Does using functions to defer evaluation of these values have anything to do with #916 (where the `Host: {host}` was 'cached' between different hostnames)? If not, could you help me understand what this change does?"
    },
    {
      "prediction": "I don't think this is a bug in TNonblockingIOThread.",
      "reference": "Perhaps the only test needed is to see if the socket is not an invalid socket? Is the >= 0 test necessary at this point?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Could this line use `url: current_user.subscription`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I was seeing `Warning: preg_match(): Unknown modifier 'a' in /path/to/project/vendor/vimeo/psalm/src/Psalm/Context.php on line 480` here"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do with the right thing.",
      "reference": "The changes in this file are not necessary."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "run `make lint` to fix"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "we will need `assert result.success` instead. result will always be not null because it returns an execution result including several metadata - when the execution fails, it'd return an execution result whose `success` attribute is false."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Can we mention how can one determine the best value given an infrastructure? Does it default to any value?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Leave this formatting the way it was please, that's the standard across all of October's files."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `go-selinux` and `go-selinux` and `go-selinux`",
      "reference": "@runcom says there is no need to use `selinux` here. `selinux` \"github.com/opencontainers/selinux/go-selinux\" The code should work fine without it."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: It might be worth defining these elsewhere as a python-type?"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "prefix it with azkaban. Maybe azkaban.server.schedule.enable_quartz?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "It'd be nice if we also caught `Unknown variable $trusted / $server_facts / $settings::` here - while I highly doubt anyone is using them (and if they are they're surely misusing them) it'd be crazy-making to have a working plan suddenly start failing with no clue as to why."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Probably need to understand/implement this one now."
    },
    {
      "prediction": "I don't think this is a bug in the code, but it's a bug in the code.",
      "reference": "It will be better to add contains check for key in hashAndFileNameToDep instead of null check over here. All of these should be inside that contains if case."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "perhaps these magic numbers could go into a Defaults module somewhere? 8140 implies the default is for puppet server. i guess that's somewhat reasonable. but if we're trying to decouple beaker from puppet, maybe this should be 80?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "style violation: { on own line"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Could we accept caseless strings (e.g. `off`, `on`, `auto`) instead of numbers to indicate the mode? Of course, we should use an enum internally (as we already do)."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The sender doesn't use `GetTipSet`, so please remove it from this interface."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We can get rid of this import then."
    },
    {
      "prediction": "I think this is the default value for the secret name.",
      "reference": "These configurations are currently overwritten in the props we provide in our config files. They need to be overridden there as well after you make this change."
    },
    {
      "prediction": "I don't think this is a problem with the `gce.OnGCE()` method.",
      "reference": "Why is error ignored here?"
    },
    {
      "prediction": "I don't think this is a bios grub boot partition.",
      "reference": ">PartitionFlagBiosGrubLegacy PartitionFlag = \"bios-grub\" [](start = 1, length = 55) I presume this is to fix a breaking change...and it's too late to fix the breaking change (since it already escaped into the world?)"
    },
    {
      "prediction": "Should we remove the `filter` here?",
      "reference": "Is this explicitly ignoring the effect of deleted rows on partition metrics or is it just that you are short circuiting any delete files (as we can't use them anyways)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I would also check whether or not this \"defaultParameters\" is null or empty to allow for people to omit it from the config file."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think event.Content is of type interface{}, so we may need %v here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Note: `editor` depends on legacy `BibEdit`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "we should probably deprecate (and display a warning) the misspelled keyword arg here rather than removing it... and then add the new one. This changes a public API and will break any code that is currently using the misspelled version."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "I'm wondering if a positive test case is needed here? Then we might compare the result DataFrame with a pre-created Koalas DataFrame."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think it was reversed"
    },
    {
      "prediction": "I'm not sure if this is the right place.",
      "reference": "The setter \"setName\" can be package-private as well"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure if this is intentional or snuck in through find/replace; while this is a correct style fix (and is welcome in another PR), it should not be done here so that the commit maintains a logical changeset."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "This makes me wonder if the TBufferTransport should have a size limit that is configurable, with a default of INT32_MAX, and then the test can make a smaller one like 4KB, and write 4KB and then one byte more, instead of using up 2GB of memory."
    },
    {
      "prediction": "I don't think this should be changed.",
      "reference": "If you use an enum for the streaming type, you wouldn't need to add each boolean as a separate attribute."
    },
    {
      "prediction": "I don't think this is a bug in MySQLdb.",
      "reference": "can you check if you can use `sqlalchemy.exc.IntegrityError` instead?"
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the right thing to do.",
      "reference": "Why we need to use recursive_mutex here?"
    },
    {
      "prediction": "I don't think this is the case for testingACMEEmail and testingACMEPrivateKey, but I don't think it's the case for testingACMEEmail and testingACMEPrivateKey is the case for testingACMEEmail and testingACMEPrivateKey is the case for testingACMEEmail and testingACMEPrivateKey is the case for testingACMEEmail and testingACMEPrivateKey is the case for testingACMEPrivateKey.",
      "reference": "am I correct these changes are related to: > I have removed a bunch of legacy functions for issuer generation ... if so, I can see why that's a valuable change but this is already a pretty huge PR and these changes to use `gen` here feel quite distant from the goal of this specific PR; they should maybe be in their own PR, to make everything easier to review? or have I missed how these changes are linked to this PR?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think that this is an unused import"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The string \"DVN_3_0\" appears in `if (!SOURCE_DVN_3_0.equals(xmlr.getAttributeValue(null, \"source\"))) {` in ImportDDIServiceBean. It's not an exact match so I don't *think* this will break dataset import from DDI but I thought I'd at least mention it."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Can you add docstring to this? Also, this might be a nit but I think `CompareCommits` or `CommitRange` might be a better name. What do you think?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "were all these ones missed in the previous PR so you are adding them now? the sources v1 and some of this? Is that right? If so, can you update the PR title"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "hmm should this be `VERSION_81` instead?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "What is the reason for increasing this?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "is there any reason we are not adding this to companion as well?   There are no CORS concerns there, so adding probably shouldn't be a problem, no? **One question about the requestId;** Are the request Ids unique to each tus-js-client request, or are they unique to an upload instance instead?"
    },
    {
      "prediction": "I think this should be removed in a future release.",
      "reference": "The formatting is a little off here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Perhaps we should import assertj for tests. These assertions are so much cleaner with assertj. Don't know whether hamcrest equivalent exist (maybe it does)."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "You should use C++-type casts instead."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Looks like each AppendHistoryNodes is its own transaction - what happens if `len(request.NewWorkflowNewEvents) == 5` but we only succeed in writing 3 of them? Will the system be able to pick up from there later? I'm _guessing_ the answer is related to the `ON CONFLICT` and `INSERT IGNORE` changes below? What does Cassandra do?"
    },
    {
      "prediction": "I don't think this is a problem with the log.WithFields(logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields{logrus.Fields}}}}) } } }})",
      "reference": "why are you replacing log here? it is defined above and contains EntryID and SPIFFEID"
    },
    {
      "prediction": "I don't think this is a problem with the `openvpnBinaryCheck` function.",
      "reference": "Why not `checkOpenvpn` as in client command?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `mocha.reporter('base')._reporter` or `mocha.reporter('base')._reporter`?",
      "reference": "> Note: Non-headless tests (that run on selenium-webdriver) need to wire up to mocha reporter to collect all the results and report them. (See `test-webdriver.js`). But for other tests this can be skipped."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `connect_to[0]` and `connect_to[1]`.",
      "reference": "I think we should apply IDNA encoding for the host here."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "No need to use `this->` here"
    },
    {
      "prediction": "I think this is a bug in the controller.",
      "reference": "I can't quite tell, is there a reason why we're finding this condition again when it was done a few lines above? Or was this a mistaken paste?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "doh. My fault, sorry."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we returning `interface{}` here? Don't we have a predefined type for `ID`?"
    },
    {
      "prediction": "I'm not sure if this is needed, but I'm not sure if this is needed.",
      "reference": "`lodash` shouldn't be grouped under WordPress dependencies"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I don't think this is a good idea to use `Note.load(noteIds[0])` instead of `Note.load(noteIds[0]).load(noteIds[0]).load(noteIds[0]).load(noteIds[0]).load(noteIds[0]).load(noteIds[0]).load(noteIds[0]).load(noteIds[0]).load(noteIds[0]);`",
      "reference": "Not sure why you want to make the distinction between null and undefined? And also `null == undefined` anyway so I think you could simply have `!noteIds` here."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Almost makes me wonder if this should default to Rpc-Context so everything defaults under Rpc-"
    },
    {
      "prediction": "I'm not sure why this is a bug in iotex-core.",
      "reference": "File is not `goimports`-ed (from `goimports`)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "would these require any account lock here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The else doesn't return anything?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "if (typeof (opts.fee) !== 'undefined' || typeof (opts.feeSat) !=='undefined') {"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `Permissions` parameter.",
      "reference": "I not sure we need to change this method's logic. Isn't no perms and invalid config?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "this is an abysmal amount of time. can you explain under which circumstances you should wait for a minute for a message?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Can we add this code to `job_package.go` and `svc_package.go`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "While you're here, can you change the casing on this so it is unexported? `nextPlanNodeIDKey` instead."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "thanks for tidying all these up, as you can tell they've been used pretty arbitrarily in the past to just exclude things from bootstrap..."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `holomap_formats` and `fig_formats` and `holomap_formats` and `holomap_formats` and `holomap_formats` are the same as `fig_formats` and `holomap_formats` and `holomap_formats` and `holomap_formats` and `holomap_formats`",
      "reference": "Again, `no_duplicates=False` would be clearer here..."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "shouldnt we stop these routines BEFORE the db closed?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It fills me with endless sadness that we can't use Selenium's own `SessionId` here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This will always need to be displayed to users."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Maybe we make an `ORIGINS` constant on the Cart model instead?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "looks like this is not needed anymore with boltdb migration. lets confirm with @fenxiong"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "shadow: declaration of \"err\" shadows declaration at line 408 (from `govet`)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the W3C Action commands.",
      "reference": "Again, the existing level is correct --- we're letting users know about something that might cause there tests to fail."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Required by the libcalico-go changes"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "You want \"current_min_count\""
    },
    {
      "prediction": "I don't think this is the right thing to do with the `sortOrder` parameter. I think this is the right thing to do with the `sortOrder` parameter. I think this is the right thing to do with the `sortOrder` parameter.",
      "reference": "Why changes in this file?"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "This doesn't look right. I think what you want here is `\\\\[([^\\\\]]+)\\\\]\\\\[[A-Za-z_][A-Za-z_.0-9]*]*\\\\]`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@AndrewRayCode thanks for contributing   Could you write/modify the specs to make sure that this description is working properly?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would have tested 304 only there."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "`TimeoutAfter` to be safe."
    },
    {
      "prediction": "I don't think we need to check for the `vsyscall_sysenter_return_pc` here.",
      "reference": "So the 32-bit tests on the new kernel hit this case? Won't they fail in debug build?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Is there a recommended quote style for attributes? I see single and double here, double further down."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "The description of `load_time` here is different from the description below..is that intentional?"
    },
    {
      "prediction": "I'm not sure if this is the default card image icon.",
      "reference": "Actually it could also be a video playlist. But music is used more often."
    },
    {
      "prediction": "I don't think this is the right thing to do with the writeConcern.w, but I don't think this is the right thing to do with the writeConcern.w, but I don't think this is the right thing to do with the writeConcern.w, but I don't think it's the right thing to do with the writeConcern.w, but I don't think it's the right thing to do with the writeConcern.w.",
      "reference": "From the ticket: > I understand why a session ID would be silently omitted for implicit sessions, but what is the reasoning behind omitting it for explicit sessions instead of raising a logic error to the user? So what this change is doing is \"silently omitting\" the session if its an unacknowledged write. I think we want to actually return an error in this case."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "You can simplify this by doing: return (EndTime - StartTime) * 60 / PointsAcrossPeak;"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think it's the time for bumping `REQUIRED_QT_VERSION` to the last LTS, 5.12. `QFontMetrics::horizontalAdvance()` doesn't exist in 5.10."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `boltdir_type`?",
      "reference": "I already set up cd10 for \"inventory_version in google analytics. I've added cd11 for Boltdir Type now"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@henrikhodne We are lazily skipping `jruby-*` here (assuming that JRuby all of a sudden start using these version numbers)."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to do this.",
      "reference": "How does this cope with values like `5.001`? Shouldn't that set precision to 0? Instead it is set to 2."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Rather than having a sleep here, we should check to see if the service we're waiting for is up yet, using something like dockerize. Not critical this second, but would be nice for later."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `execa`?",
      "reference": "I'm not sure if there are any links to swap for Handosntable package. Should this be a top lvl script?"
    },
    {
      "prediction": "I think this is not the right thing to do.",
      "reference": "It seems like it's too big now: can we remove signal_frame_extra_size from line 537? That should only be needed when placing xstate separately. It seems like it isn't needed at all for pending? Also, if we have special heap align forward for us, we don't need this align here either."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the command line, but it's not the right thing to do with the command line. I'm not sure if this is the right thing to do with the command line.",
      "reference": "Just double checked the `-in` operator. It's PS3 only, so we might want to change `$_ -in $allowedArgs` to `$allowedArgs -contains $_`"
    },
    {
      "prediction": "I don't think this should be used.",
      "reference": "Might as well use translate here, as @jcsteh suggested"
    },
    {
      "prediction": "I don't think this should be a string, but it's not a string, but it's not a string, but it's not a string.",
      "reference": "Definitely an improvement as long as the old tests pass (i.e backwards compatible)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "nit: non functional change"
    },
    {
      "prediction": "I don't think this is a good idea to do with the `AWS_SHARED_CREDENTIALS_FILE` environment variable.",
      "reference": "The file is not required - if you're using an IAM instance profile, for example. I'm not sure we can error 100% of the time if it's missing. @randomvariable any suggestions?"
    },
    {
      "prediction": "I think this is a bug in the compiler.",
      "reference": "There is a very similar line `lowType = expr.Low.Type().(*types.Basic)` a few lines above this line. Can you change that in the same way?"
    },
    {
      "prediction": "This file is not used by anyone who may have a copy of the License.",
      "reference": "New files should be copyright Hyperledger Besu Contributors."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `run_script` method.",
      "reference": "if I give a non-existent script, then I don't get an errors. I would have expected the `copy` method to raise, but maybe `net-sftp` silently exits?"
    },
    {
      "prediction": "I think this should be a list, not a tuple, not a list, or a list of tuples, or a list of tuples, not a list of tuples, or a list of tuples, not a list of tuples, or a list of tuples, not a list of tuples, or a list of tuples, not a list of tuples, or a list of tuples, not a list of tuples, or a list of tuples, not a list of tuples.",
      "reference": "@itholic can you also update the parameters in the docs?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The super impl Spliterator.getComparator() throws an IllegalStateException by default. Is it really necessary to return null? If null is used somewhere it will throw a NPE, which is roughly the same as throwing an IllegalStateException. I'm just curious - I'm sure there is a reason!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need to do the same in Avro `WriteBuilder` too? I don't think we use that method right now but should make sense for consistency. We already handle that for Parquet."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "can you make all the `_` into `-` to be consistent with the other options?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to use.",
      "reference": "What do you think of renaming this file to `stack.go` or `cfn_stack.go`? `common.go`/`util.go` don't provide us anything descriptive about the contents of the file."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `opentelemetry.Exporter.OpenTelemetryProtocol.Tests` package, so we can't use `opentelemetry.Exporter.OpenTelemetryProtocol.Tests` package.",
      "reference": "It isn't a very effective example if it requires access to the internals   I can't tell just looking at the diff why this is needed, can you provide a little context?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `bolt/transport/local.new` method.",
      "reference": "Why does this include `bolt/inventory`?"
    },
    {
      "prediction": "Should we remove the key?",
      "reference": "We called `t._1.equals(...)` where `t._1` potentially could be `null`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `aria-valuenow` attribute. I'm not sure if this is the right thing to do with the `aria-valuenow` attribute.",
      "reference": "I don't think we should include the `hasAttribute` test here. Even without aria-valuenow, it's still an aria range element. This check is going to make reuse of this function problematic. Better to move the attribute check part outside this function IMO."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Shouldn't it be optional?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "would be helpful to make these a package level constant so they are accessible to the user. similar to Service Name. Not directly related note, v2 SDK ServiceName should be renamed to ServiceEndpointPrefix."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Duplicate call to the method. Better to put in a variable."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "\"and returns that\" -- it looks like this method has no return value."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Modifications are also needed for PolygonMask."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Does this really make a difference?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Added a validator for _root_, which is now added automatically since the schema used here declares _root_."
    },
    {
      "prediction": "I think this is the default value for the \"read.split.open-file-cost\" property.",
      "reference": "The other properties are `file-open-cost`, not `open-file-cost`."
    },
    {
      "prediction": "I don't think this is the right thing to do with libunwind.h?",
      "reference": "confused by this: what we need here is not libunwind but libunwind-dev right? Why skipping detection?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "just in case helps, it this related with this PR?"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "This is incomplete I think (at least source_address and ip_address are missing)"
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function.",
      "reference": "We have a `stop` method here, we should probably be calling that instead of just exiting. There could be important resources to close or cleanup nicely now or in the future."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "fixes ArgNullEx when using both `x-ms-parameter-grouping` and media type `application/xml` in the same operation (issue #2236)"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "`NotFound` is a generic error code derived from the HTTP response message's status code, and can be returned for any S3 operation that responds with a 404 status code and no other error code present. Due to this the constant `ErrCodeBucketNotFound`. In addition, these constants are generated based on the API model defined by Amazon S3, modifications to the file directly will be lost during regeneration of the API. With that said, we are looking at ways to work with the Amazon S3 team to better represent this error in a way that is more easily consumed."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it would be better to do it with the host/win/pkg.rb level.",
      "reference": "@johnduarte I was curious about the case when the operating system was neither `osx` or `win`; in this case, the test will indeed pass, but nothing will have actually really been tested. Should this have a `skip_test` condition at the top?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think this example was included by accident? It doesn't seem to belong in this PR (but a separate PR with this would be nice!)."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the request body?",
      "reference": "Just fixing a bunch of outdated java docs in this file"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "I think it may be safer not to touch Concurrent to normal."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "is this for everything, or just legacy?"
    },
    {
      "prediction": "I think this should be a `Promise` object, but it's not a `Promise` object, but it's not a `Promise` object, but it's not a `Promise` object.",
      "reference": "I think this should be a `MongoError` right?"
    },
    {
      "prediction": "I don't think this is a problem with the `testcommon.TestSite` class.",
      "reference": "This is currently a db.tar.gz with just one .sql file in it. It might be worth another test (or maybe I'll find one) that has more than one sql file in it."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Why these changes to existing tests?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "It should be `IsNullOrWhitespace` I believe, since we're going to trim the value afterwards (and I just realized the other configuration keys have the same issue)"
    },
    {
      "prediction": "I think this is the same as `select_implementation(target, additional_features, provided_features)`",
      "reference": "This is just for consistency + searchability with the transports"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "please run gofmt."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "thats kind of a bummer, why do we have to give it full access? if it is just for the private interfaces i'd personally rather have those interfaces pollute the public exported symbols than open the tests up like this."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Because this is an unexpected situation so can you add a log here to help us figure out what resource is causing this problem?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "just observing that this innocent looking change seems important to this PR. Previously this data had disappeared from the state."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Actually, I do have one question: You mention that each warning is for a different range. Should we add the rowcounts instead of using the max?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "it is confusing to return ID as Name"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "body is being used here for the first time without every being populated. This will error. To run tests do `./go clean test_py` and that will run the Firefox tests"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "commit mesasge: I would append \"...Kernel::loadClassCache() method call\""
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Keys.COMMAND seems to be an alias to Keys.META. That isn't mentioned?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You can move this import down to before line 8 (import org.junit.Test;)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It's okay to add the `scanner_index_id` here. But we still should keep the `inventory_index_id` reference because it will help the user to know right away, which inventory the violation is coming from, without having to do another lookup."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "this shouldn't be beforeClickOn, but rather beforeSubmit? and added to WebDriverEventListener. Since submit does not synthesize the 'click' events, this isn't accurate."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should this be I18n'd?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "We don't typically use `ImmutableList` to avoid leaking it in methods that are accidentally public or purposely part of the API. I'm +1 for returning `ImmutableList.copyOf(errors)` below, but I don't think we should guarantee the list will be an `ImmutableList`."
    },
    {
      "prediction": "I think this is a test case, but it's not a test case, but it's not a test case.",
      "reference": "@greglandrum Is this test sufficient?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "I think Rails complains about the `null: false` part if we ever decide to roll this migration back. Might need to split this up into separate `up/down` methods to handle that."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "I don't think we need this line. You're logging in `waitForContainerTransition()` anyway"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Shouldn't the `:attribute` placeholder appear?"
    },
    {
      "prediction": "I'm not sure if this is a struct like, but I'm not sure if it's a struct like, but it's not a struct like.",
      "reference": "Could you update this to `structLike` instead of `arg`?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "I only now spot this `freebsd,!baremetal` in the code, which doesn't make a lot of sense. The fact that there is `linux,!baremetal` is because baremetal targets pretend to be linux/arm to get the standard library to compile. Such a `!baremetal` exclusion is not necessary for FreeBSD. But this is not something that needs fixing in this PR."
    },
    {
      "prediction": "I think this is a bug in glnx_fd_close.",
      "reference": "Ugh, we were using cwd? =("
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "This can probably be removed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "put this sentence in `if (onResult_) { }`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `forseti_server_conf` in the `forseti_config_validator_constraints` file.",
      "reference": "Will this always be started up as default? Is there any impact to the VM in terms of load and memory usage?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Thanks for fixing the typo's but given that this is a fork of the other commandline.cs file they will still exist there :( Part of the reason forks suck."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This doesn't seem related to docs? :)"
    },
    {
      "prediction": "I think this is the default value for quietTimeEnabled and notificationDuringQuietTimeDisabled.",
      "reference": "Having a negative in the variable/method name makes the code harder to read. Also, you inverted the logic but didn't invert the default value. I suggest sticking to the original name."
    },
    {
      "prediction": "I think this is the default value for `ForceTraceWriteLine` and `ForceTraceWriteLine` is set to `true`.",
      "reference": "Think you need to keep `RawWrite` around as obsolete until NLog6 (Property that just assigns `ForceTraceWriteLine`)"
    },
    {
      "prediction": "I don't think this is the case. I don't think this is the case.",
      "reference": "I would expect this to be named *get* not *set*: it's a query; it's not setting some persistent state."
    },
    {
      "prediction": "I don't think this is a problem with the `pipeline_definition_sensor` in the `pipeline_definition_sensor` module.",
      "reference": "maybe should rename this to be `run_status_sensor_definition.py`"
    },
    {
      "prediction": "This file is not used by anyone who may have a copy of the License.",
      "reference": "Do we want to add the other write options in this PR or keep the refactor separate?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "either make this a config or a constant we can define at the top. Burying this in the code is no good."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same about new metrics. Can we avoid adding them?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the right thing to do.",
      "reference": "I know this is a port from the previous PR, but I am wondering if we can take the chance to improve the naming? `--vpc-host-project-id` ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The test description says it's \"by reference\". We should change the description"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "A C# newbie question here: would it make sense to declare Id as an abstract property so any subclass Must have its own Id?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "just looks like you should return an **empty map** with nil error"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "could you also update the starting log at L146?"
    },
    {
      "prediction": "I think this is a bug in the DBus library.",
      "reference": "Also this probably should be `error.As()` or something like it."
    },
    {
      "prediction": "I'm not sure if this is a standard command name, but it's not a standard command name.",
      "reference": "This is Safari specific and should be defined somewhere in the `safaridriver` namespace"
    },
    {
      "prediction": "I don't think this is the case for `ostree-mount-deployment-var` and `ostree-prepare-root`",
      "reference": "Let's maybe be nice and `unlinkat()` here in the interest of having `/run` be less littered. Or in addition/alternatively, make the file `/run/ostree/initramfs-mount-var` since we already made `/run/ostree/` for the deployment staging bits."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Not sure if this doesn't require explicitly adding this library to cmake."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "we should probably deprecate (and display a warning) the misspelled keyword arg here rather than removing it... and then add the new one. This changes a public API and will break any code that is currently using the misspelled version."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "seems reasonable to also want to include the 'to' location?"
    },
    {
      "prediction": "I don't know how to do this with `opts[:collect_perf_data]`?",
      "reference": "This `if` statement can be merged with the above `if opts[:collect_perf_data]`."
    },
    {
      "prediction": "I think this is a bug in MongoDB.",
      "reference": "But won't we do case-insensitive matching for all the drivers? For example, we will get the revision field case-insensitively. Let's make this case-sensitive. I think the way the mongo driver works, by lowercasing field names, will be OK with that."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I believe this should be on `workshops/show` now, not `products/show`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If we return error when we are unable to found country in database, using country detector would be much easier - if error was not returned, that means country was returned :) This doesn't have to be solved in this PR, but since you're adding such case, we can add a `TODO` just to track this :)"
    },
    {
      "prediction": "I don't think this is the case for the `DD_DOTNET_TRACER_HOME` environment variable.",
      "reference": ".NET Framework: Fallback to `DD_INTEGRATIONS` if `DD_DOTNET_TRACER_HOME` was not set."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you use `authority, _, path = rest.partition(b\"/\")` here? That should make stuff a bit cleaner."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't think this needs to be a float if its a number of seconds... :)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Please add \"Array\" back, right now it's not a proper sentence."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "@tkaessmann when I ran tests I saw this line has a bug. It inverts the SHOULD and MUST. Hopefully I fixed it and merged it without the bug."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "There may be another bug, it looks like we're already in a `if telemetryConfig.Enable` block at this point, maybe that block should be unnested?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "This... looks like it plainly didn't work before? Good catch. I would suggest we change the logic here to 1. Check if `self.headers[\"content_type\"].startswith(\"multipart/form-data\")`, and if that's not the case, add a content-type header with a random (?) boundary. The point here is that if someone assigns to `.multipart_form = ` in their addon, the header should be updated accordingly if the request was not multipart before. 2. *After* that, call `self.content = multipart.encode(self.headers, value)` (as we do right now)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "importShadow: shadow of imported from 'github.com/stretchr/testify/require' package 'require' (from `gocritic`)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Wouldn't it be enough to change the condition in the for loop to `link_state != IBL_UNLINKED`?"
    },
    {
      "prediction": "I don't think this is a bug in glib/glib.h.",
      "reference": "I'm not familiar with signed setups, but this does not seem to offer a way to choose between GPG and signapi verification. Are they usually either both enabled or both disabled? Would this be better suited as a verb with flags for different methods?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "assignments should only be cuddled with other assignments (from `wsl`)"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "would it make sense to mock oauth in a way that we direct a user to this endpoint on login (in a test)?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's a good idea.",
      "reference": "Since these two lines use the same logic, it may be cleaner to use an `if` statement rather than duplicating it."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "unnecessary blank line"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Nit: no need for \"to\" at the end of the doc because it already uses \"to which\"."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I would just say \"Signed before publishing.\""
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We can just include the public UDPv4TransportDescriptor header here ..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do we need this change?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "These three atomic functions done separately are not atomic. There is a possibility of data race, as nothing is guarding Total in between lines 182 and 183. Total got on line 182 may be changed before new value is stored on line 183 by some other goroutine resulting an incorrect value. Mutex should be used."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Is this because you don't have % on your version of Slot? I don't really care either way."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please use var declaration for variables you are declaring. I could not find one for userInjectedExpandableRowHeaderColDef and finalExpandableRowHeaderColDef. Also code styling in the if block needs to be corrected."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If cachedLibPath > 200 bytes, it will overflow errString."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Talked this through with a few more folks. I think it would be better to flag prohibited attributes for review, instead of outright failing them. ARIA labels are used fairly liberally. We don't really know if they are actually needed whenever they are used."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Let's keep it to avoid the diff"
    },
    {
      "prediction": "I don't think this is a bug in this class, but it's a bug in the future.",
      "reference": "nit: not directly related to this PR, but shall we use `ImmutableSet` for consistency?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Layout/DotPosition: Place the . on the previous line, together with the method call receiver."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `newAuthToken` and `newInstanceUrl` and `newInstanceUrl`?",
      "reference": "We send the `instanceUrl` encrypted, but never bothered to decrypt it. I guess it was working because we never did any org split testing where the `instanceUrl` actually changes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can this be moved to QbftBlockHeaderFunctions class as it is only used for qbft"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the exception condition?",
      "reference": "`Tags` now comes from the `PropertyBagHolder` base class."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not sure where this should go, but one of the `get_extents` methods should mention that `range_type` can be `'data'` or `'combined'` (are there others?). I found out those are the two expected values by searching the code..."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "please revert all of this stuff in core.. I'll take another pass after. cheers and thanks for the help!"
    },
    {
      "prediction": "I'm not sure why this is a bug in SparkCatalogTestBase.",
      "reference": "Why was this needed?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I see that CI found a couple test hangs, maybe your `TogglePrefetcher` change below wasn't enough and this still needs to be a `go` invocation for some reason?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I do not understand this change"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It would be helpful to clarify this is only for unmarshaling a response. not marshaling a request."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I have no explanation for why this test wasn't erroring before... There are two applicable nodes in this tree, one passes, the other fails."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Remove the \"rm\" from the end of \"HAVE_CONFIG_H\""
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Non-Blocking: This might be too trivial. It doesn't allow us to test that it's being callled."
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "Not sure why the ternary expressions are used here, since the true and false results are the same."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is `vertigo` another name for Vertica databases?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "That doesn't do the right thing - it strips any of the characters m, a, i, l, t, o and :. It'd probably be cleaner to do this before converting the URL to a string."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why the white space changes?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is now outside the mutex, so could race."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "hmmm did this pass spotless check? I don't think we typically use wildcard imports"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`lockBeforeLock` -> `lockBeforeGet` (here and everywhere below)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Do we need to internalize net.sourceforge.pmd.lang.java.ast.JavaParserConstants on master, so that we can rename it?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "The GUID here was incorrect, because of that, Vault plugin loading was failing. Should I change to any correct GUID, or it has some special meaning?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "just confirming: if we remove explicit Collect(), then we are relying on the provider dispose... which has a hard-coded 5000 msec to finish flushing. On the other hand, if we keep explicit Collect(), we can pass an explicit timeout to it. (we were not doing it now and was relying on Infinite timeout). Net effect of this change in test code: Previously we would wait indefinitely for Collect() to be over. With this PR, we hope Collect() will be over in 5 secs. If we ever need more than 5 sec, we need to bring back Collect(maxTimeInMilliSecs..)."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "What do you think of a name like azkaban.server.logging.kafka.brokerList? This way the name signals that this is a server config."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe change into `return _concurrentWrites ?? PlatformDetector.SupportsSharableMutex` ?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "indentation of resulting file is different between 11 and 8 where 8 doesn't indent lines and 11 does"
    },
    {
      "prediction": "I don't think it's a good idea to do this.",
      "reference": "Do we still need to return the `Response` here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Here `global.VERDACCIO_API_URL` I'd use something different as `global.TEST_VERDACCIO_API_URL` then when you search by `VERDACCIO_API_URL` we don't confuse with `window.VERDACCIO_API_URL`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This is totally fine, but consider whether in the future a YAML input format would be better. If so, we can plan for it."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "This should be `DD_TRACE_CONVENTION` to follow our ... conventions."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Be careful memory leaks. memory leaks occur when getters.getAliasProp == nullptr . right?"
    },
    {
      "prediction": "I don't think this is the right thing to do with a map[string]*perAccountCache",
      "reference": "Why not just a time.Time?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Please do not submit a commit that is not part of this PR."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is small braking change: there is no way to clear description any more. If value is empty string, description will not be updated at all. It will affect existing Thrift endpoints also."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Can you open a separate PR with this patch? It seems valuable outside the context of this PR!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would suggest to have plurals in the api `\"/chunks/{address}\"`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Let's just not do this. We don't have LabelAtoms.O17 here. This is just a short-cut to avoid needing to write out a more verbose function like: 5O\" - 5O i.e. Add 5 x 17O atoms to replace 5 x 16O atoms. This was the original implementation in Skyline before I added the checkboxes to denote simply labeling all atoms in the amino acid."
    },
    {
      "prediction": "I don't think this is the right thing to do with `approval.mini_approval`?",
      "reference": "1:D100: Docstring missing 23:D400: First line should end with '.', not 'p' 23:D200: One-line docstring should not occupy 3 lines 36:D400: First line should end with '.', not 'n' 36:D200: One-line docstring should not occupy 3 lines 48:D400: First line should end with '.', not 'p' 48:D200: One-line docstring should not occupy 3 lines 63:D400: First line should end with '.', not 'p' 63:D200: One-line docstring should not occupy 3 lines 76:D400: First line should end with '.', not 'p' 76:D200: One-line docstring should not occupy 3 lines"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Adding a warning or an error in the Thelia log would be a nice idea."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: `Set` (and swap `forEach`s for `for (const i of CONNECTION_EVENTS)`)"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "nit: Is this `using` statement still needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Dont need to cast `string` -> `string`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why doesn't the API return an error in this case?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure how particularly useful these exceptions are. Seem to be exceptions required in copying and pasting the EndpointResolver over. I wonder if it makes sense to move these out of ``exceptions.py``"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can we re-add this? I think that grouping is useful (though would be open to putting them in a mixin or something)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Overall LGTM, one nit is that I think `partitionFields` here would be good to be renamed so that it's easy to tell it's just for collision detection. Also I wonder if we want to do this check for other transformations too (e.g. bucket, and record numBuckets in the string), so that we might be able to combine `fields` and `partitionFields` into potentially something like a LinkedHashMap?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Don't need the `or None` here as the flag will already default to None. Also, `some_dict.get('foo')` will also default to `None`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please, use the default padding here."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "let's actually use the direct include: `require('../core/error').MongoError;`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `new-instance-open-target.window` option.",
      "reference": "You're missing a space before the `\"` here and below, but I'll fix it up when merging."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "remove this debugging code?"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack, but I think it's a hack, but I don't think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack, but I think it's a hack.",
      "reference": "s/`terms text`/`terms's text`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": ":bike: :derelict_house: , but maybe the default option should be `multipleResults: false` or `combineMultipleResults: false`? i feel like `replaceResultInFormWithNew` is very verbose but also doesn't immediately clarify what it's for."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Line is too long. [87/80]"
    },
    {
      "prediction": "I think this is a bug in RDKit.",
      "reference": "Are you using an automated tool for sorting the imports?"
    },
    {
      "prediction": "I'm not sure how to do this with the `fetch_bigquery_dataset_policy` method?",
      "reference": "If this is `project_number` now, can we also update the `id` the description?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "* This will defer until the function returns. Are you sure this won't happen multiple times. * Alternatively, why is the deadline timer not defined outside the outer loop? * More generally, why are we looping in the first place instead of reading one frame and returning?"
    },
    {
      "prediction": "I don't think this should be used in the future.",
      "reference": "Should we rename the traces parameter now that this isn't just traces?"
    },
    {
      "prediction": "I think this is a bug in the drm_mode_atomic_commit() method.",
      "reference": "I don't think it makes sense to have both `TEST_ONLY` and `NONBLOCK`. We should probably leave `NONBLOCK` out."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Need to remove the surface destroy listener (and `wl_list_init` it so that `touch_point_destroy` still works)"
    },
    {
      "prediction": "I don't think this should be the right thing to do here.",
      "reference": "create ticket to investigate this"
    },
    {
      "prediction": "This is a hack.",
      "reference": "If we want to expose this for FFI use in the standard library, it needs to get either a `pony_` or `ponyint_` prefix to its name, for cleanliness of the function namespace. `pony_` means it is a public API meant for use by third party code, whereas `ponyint_` means it is internal. Unless there is a good reason to make it public, we should prefer to keep it internal because public functions require us to treat any changes to them as breaking changes in Pony. So, this function should end up named `ponyint_address_length`, or something else with that prefix."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Fuse for shared volumes is a px specific implementation. libopenstorage doesn't know about it, right? So should this be called DeviceVirtualMount (or something similar) instead?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`bool` vs `BOOL` in native side :)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `package.json` or `package.json` or `package.json`?",
      "reference": "I think maybe you moved it to util but this is still around and it should get it from util instead."
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `current_user` and `current_user` and `current_user` parameters.",
      "reference": "Do we need to test the redirection?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Tsts, that's why... activity leak about to happen"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "You should do a select here IMO just to be safe so we do not block forever."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I'll replace this with the actual outbox object soon."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Providers are called *before* `setUp()`, so I don't think you can access properties here."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "While this allows it to be applied does it correctly cause the entire class to be skipped?"
    },
    {
      "prediction": "I don't know how to do this with `dist.get_rank()`?",
      "reference": "clean unnecessary modification."
    },
    {
      "prediction": "I think this should be a `undefined` property, but it's not a `empty` property, but it's not a `undefined` property.",
      "reference": "I think these assertions want to be `.to.not.exist` which would pass for `null` or `undefined`"
    },
    {
      "prediction": "I don't think this is a problem with the `gocloud.dev/howto/secrets/#vault-ctor` example.",
      "reference": "Don't think you need this since this is not a URL example."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe a test to check if the generated value is within the boundaries would be nice, what do you think?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with UTF8 encoding?",
      "reference": "Suppresses UTF-8 BOM in outputs"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "order wrong for \"outgoing and incoming\""
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "We know it's a boolean and it's in the MemoryCircuitBreaker, why not simply call it `enabled` (like many other Solr plugins do)?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `include_team` column.",
      "reference": "Should team be a \"feature\" that can be \"included\" or a type? In code it seems to me that a `team` flag makes sense."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why is this called update params when it's updating project info? Should p called project?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `history_tree.insert(shard_id, tree_id, branch_id, data, data_encoding)` and `history_tree.insert(shard_id, tree_id, branch_id, data, data_encoding)` and `history_tree.insert(shard_id, tree_id, branch_id, data, data_encoding)` and `history_tree.insert(shard",
      "reference": "`upsertHistoryTreeQuery` is a better name for this query now. Is it ok to change history?"
    },
    {
      "prediction": "I don't think this is a bug in Nethermind.Core, but it's a bug in Nethermind.Core, but it's a bug in Nethermind.Core, but it's a bug in Nethermind.Core, but it's a bug in Nethermind.Core.",
      "reference": "b did not mean branch - it meant the next version - so probably better to be able to release from a tag on the branch so we can create a hotfix branch of the 1.4.1 tag and tag it 1.4.1b and then version is picked as 1.4.1b"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Keep the mpi.h include, just move it to after adios2.h and guard with the ifdef. Otherwise everything else looks good."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't this be something like `rootmountmode` to fit the pattern of the other fields' serialized representations?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why were we initializing here in the first place?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should be removed, and instead set the logger to None."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Storing a reference to source data isn't the best choice. Maybe you can find a different way (without storing the reference) to save removed data?"
    },
    {
      "prediction": "I don't think this is the case for debug Trafodion builds, but I don't think this is the case for debug Trafodion builds.",
      "reference": "Is the tutorial going to move to the new Trafodion website or will it stay on the Confluence wiki? (Check with Gunnar.)"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "maybe call it `fromRetryTaskV2Failure`"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The diff for this class is difficult to walk through because I reorganized it to be much more clear. There are improvements throughout, but the most important are in the new `createSmokeTest.*` methods."
    },
    {
      "prediction": "I don't think this is the case for the `img_norm_cfg` parameter, but it's not the case for the `img_norm_cfg` parameter.",
      "reference": "We suggest keeping this logic in lines between 173-175 to restrict its influence."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "why not ? maybe another phpstan plugin"
    },
    {
      "prediction": "I think this is the default value for the `cancellationToken` parameter.",
      "reference": "That was a really bad CR from me before if I did not spot it."
    },
    {
      "prediction": "I don't think the lock file is already locked by the previous process.",
      "reference": "Does this resolve the scenario when the user-triggered forseti process is running, and it would be killed by the cron job restarting the server?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this happen somewhere else now?"
    },
    {
      "prediction": "I don't think this is a bug in Tizen 5.0.",
      "reference": "Remove trailing space at this line, amend the commit, and then force-push."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `go.opentelemetry.io/api/trace` or `go.opentelemetry.io/api/core` or `go.opentelemetry.io/api/core`?",
      "reference": "This should be grouped together with the import of \"go.opentelemetry.io/{api/core,sdk/export}\" below."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "What's the impact to people upgrading to the new version? If they don't change their file names, they'll suddenly be broken. While I agree that your naming makes more intuitive sense, I think we need to maintain backwards compatibility. Please choose a new rules file name for the new scanner and keep ke_rules.yaml for the existing version scanner."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Shall we add some docstrings clearly to describe when to use which clearly? For example, `spark_frame` now should always be used via `df._internal.applied.spark_frame` for Spark DataFrame APIs that internally creates new query execution plan with the different output length. For expressions and/or functions, `df._internal.spark_frame` should be used together with Spark column instances, in order to avoid the operations on different DataFrames."
    },
    {
      "prediction": "The `index` argument is ignored.",
      "reference": "nit: `.` at the end of line?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I'm not sure I agree that this should take priority over \"Loading\"."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `deploy_mode` property.",
      "reference": "Was this an intentional deletion? Why not just allow overwrite of `deploy_mode`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "better to call it as syncCVRStatus.. just syncCVR is very confusing"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "should we make this not a pointer? so that when we embed the struct a copy is made instead of modifying the original object."
    },
    {
      "prediction": "This is a hack, but I'm not sure if you want to use the `get_app_settings` method, but I'm not sure if you want to use the `get_app_settings` method, but I'm not sure if you want to use the `get_app_settings` method, but I'm not sure if you want to use the `get_app_settings` method.",
      "reference": "Does this mean that `kinto_redis` is required to run tests?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "will this ensure the indexes for ordered writes as well?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Put `BoolArray` first?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I believe this whole file can be deleted now."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "We should specify format for a user. I.e: Integer, 1000 == 1 MYST"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does the errors returned from these controllers indicate which controller threw the error? If not, there might be some value in making the \"CustomControllers\" type a `map[string]func(ctx context.Context, sc *server.Context) error` with the name of the controller as the key and include the key in this error string. This would apply for below as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "maybe at least pull the file identifier arg out of the if?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "You can most likely remove that (and the try/finally) too, as we shouldn't have any flickering from removing/inserting tabs anymore now."
    },
    {
      "prediction": "I'm not sure if this is a local hook. I'm not sure if this is a local hook. I'm not sure if this is a local hook. I'm not sure if this is a local hook. I'm not sure if this is a local hook. I'm not sure if this is a local hook. I'm not sure if this is a local hook. I'm not sure if this is a local hook. I'm not sure if this is a local hook.",
      "reference": "Could you add `s` to `@return`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `path_for` method.",
      "reference": "Moving this code inside the last case statement doesn't seem right. Why are we defining `name` and `is_relative` variables there if we aren't using them anywhere?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Will cause any bugs without this change? I've seen this code block(L293-302) many times... ;-)"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "You are opening a door to race-condition-hell by returning an unprotected dictionary. I recommend that you return `IReadOnlyDictionary` that only works on the platforms where it is known."
    },
    {
      "prediction": "I think this should be a `Promise` instead of `it.skip('should return a promise when no callback supplied to forEach method', function(done) { it.skip('should return a promise when no callback supplied to forEach method', function(done) { it.skip('should return a promise when no callback supplied to forEach method', function(done) { it.skip('should return a promise when no callback supplied to forEach method', function(done) { it.skip",
      "reference": "also seems we should not skip this test"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is mostly for my understanding: is `DeleteFile[] deletes` a mandatory builder param now for file scan tasks? If not, from a v1 / v2 compatibility standpoint would it make sense to add an overloaded constructor?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Can the error message reflect the purpose of the query more closely? Something like \"Error fetching executions queued for a long time\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are you making it so startup script HAS to be in sources?"
    },
    {
      "prediction": "I think this is a problem. I don't think this is a problem.",
      "reference": "Might be more clear to just have one if statement?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "remember that logger methods will do string interpolation automatically anyway, so you should be able to do `logger.error('message %s', var, exc_info=True)`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Perhaps rename to `render_service_args_struct`?"
    },
    {
      "prediction": "I don't think this is a bug in go-filecoin/internal/pkg/crypto.",
      "reference": "clean the name"
    },
    {
      "prediction": "I think this is a bug in knative-gcp.",
      "reference": "I think we would expect StatusNotFound instead of StatusForbidden?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since this is a recurring theme, would it make sense to have an ioencode interface for it like `ioencode_rank()` that takes an integer rank like before?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is it a concern that we initialize these fields irrespective of whether resources like cgroup/volumes are enabled or not?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Wouldn't this be the first panic in yarpc? What do we do for transport validation? Return errors?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "have you envisioned other cancellation reasons?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For the record, class-string is now suported by PHPStorm. Don't know if it's worth moving it to `@phpstan-param` then."
    },
    {
      "prediction": "I'm not sure why this is a bug in the code, but I'm not sure if this is a bug in the code.",
      "reference": "This prevents negative IDs, but it doesn't check for too large IDs. You should probably just do the same check you do for `QWebengineScript` here as well."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This might be very confusing. Maybe `resource-tags`? I"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "We may use `_pair` to wrap `dilation`."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "what's with `setReadonly`? Why we deleted it totally?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Currently I think this is not acceptable. I think the value should be chosen by the author of the parser. (Personally \"type\" is better than \"typename\".)"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Is this excessive?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Ohhhh I see, this change was previously having *no effect* - I had thought you meant we were doing something like bind mounting the initramfs' `/etc` as the real `/etc` but we'd clearly notice if that happened, we'd be missing all sorts of config files etc."
    },
    {
      "prediction": "I don't think this should be a string.",
      "reference": "I think this needs a more specific name, like `sequenceNumberOverride`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Ought we just raise an exception if the adapter isn't defined?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should this have been removed? We still set the region to \"aws-global\" in v3model.go#L115"
    },
    {
      "prediction": "I don't think this is a problem with the request.headers.get('Accept-Language'),",
      "reference": "You could shorten this to `qs or None`. But why not just build a dict of parameters we want to include and only add `querystring` if there's something here, similar to the way you do in the error view?"
    },
    {
      "prediction": "I don't think this is a blocking operation.",
      "reference": "sorry if I'm missing it somewhere else in the code, but do you need to create a `ticker := time.NewTicker`?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Inline this, as we don't use it again."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I think the instantiation of the new objects i.New() and T.New() need to be done in a function to have local variable and reduce the amount of memory used."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This is probably more digits than needed - perhaps rename OneOverK0 to IonMobility instead"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "End with 'Method', so: - FlattenedAsyncCallSettingsMethod - FlattenedAsyncCancellationTokenMethod"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `gcp` or `internal/secrets`?",
      "reference": "`localsecrets` should be updated in the same way."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We'll want to PR a spec change into github.com/algorandfoundation/specs. (Side note: It might or might not make sense to combine this protocol upgrade with Tsachi's protocol upgrade for fixing the reward rate calculation.)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Use `FullBlock`, it comes from the same package."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "do we plan to use anything else than flask for making HTTP requests inside localstack? if so, it maybe makes sense not to strongly couple to flask for now, and just leave the type of the `request` function parameters open for now."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I think we should make this a separate test case: it seems like making the precondition fail is the test case that would ensure that this escape hatch worked. Otherwise, if it's always true, then it would be the same as if the escape hatch didn't modify the outgoing request."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Error return value of `s.idx.BuildIndex` is not checked"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "What's the reason for excluding those from the fuzzing here? You probably could just add some inner type via `functools.partial` like below with `FormatString`."
    },
    {
      "prediction": "I'm not sure why this should be used in tests.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "Its this golint or govet stuff?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "These are good cleanups: I didn't realize there were so many like this in the samples and tests. But given that there are quite of few of these mcontext changes I would separate these into their own PR (no need for an issue: iX branch) since they are logically distinct. Cleaner history, simpler revert paths, etc."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "  This is just a random struct equality, no value here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just spotted the `local` on here; that shouldn't be needed - no reason to limit this config to env vars only"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `get_param_values` function.",
      "reference": "I had some weird issues when importing ``from .. import util`` getting the wrong utilities, hence I did this."
    },
    {
      "prediction": "This file is covered by the GNU General Public License.",
      "reference": "Please remove this line."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "should this state that we're falling back to `:acceptable_exit_codes`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think this works. The dataframe object is encapsulated in the value parameter. This might be the root of the failing checks."
    },
    {
      "prediction": "I don't think this is the case for a standalone server.",
      "reference": "Why was it necessary to add this check against `this.servers.size`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This tests for < 0 but the error message says it must be > 0. The `if` should probably be `<=` to match the message."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Short circuits when it's something like a WebPackRequest, which we should instrument and test specifically."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should this be true now by default?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "/DispatcherStatistics ? /statistics is a bit confusing with /stats"
    },
    {
      "prediction": "This is a hack.",
      "reference": "nit: Wondering if we should simply filter on `\"tail: unrecognized file system type\"`, or is the type identifier `0x794c7630` always the same?"
    },
    {
      "prediction": "I don't think this is a good idea to use `aws:{\"identifier\":[{\"kubernetes.io/cluster/fake-infraid\":\"owned\"},{\"openshiftClusterID\":\"%s\"}],\"region\":\"us-east-1\"},\"clusterID\":\"%s\",\"clusterName\":\"%s\",\"infraID\":\"fake-infra-id\"}`",
      "reference": "I think the goal of using `fake-cluster-id` was to make it sure clear that this is a fake cluster, replacing this with UUID only now makes these clusters look very similar to real ones which can cause problems.. any reason why we didn't go for the original recommendation from slack thread of `fake-cluster-UUID` @twiest"
    },
    {
      "prediction": "I don't think this is the case for a try, finally, or finally.",
      "reference": "I need to spruce up my `mypy` knowledge but I think this is incorrect. Using `T_Node` twice makes it so that both should be the same type. I think this would be better: `Tuple[Optional[T_Node], Optional[nodes.NodeNG ]]`. It might even better to do: `Union[Tuple[None, None]. Tuple[T_Node, nodes.NodeNG ]]` as that shows that `None` should always pair with `None`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: below on line 449 we use `%v` to print an error - perhaps would be nice to do it in the same way in both places (but probably not that important). Similar in other places in this PR."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not against adding a kill event, but we need to do it properly, please. That means listing it in events.py, adding docs for it, and so forth."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this line can be lifted outside of the if-then? In fact only CreateString / CreateSharedString needs to be inside of it."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I think the `EpisodesApplyActionFragment` is unused now. So please delete it :)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `--log-level` option.",
      "reference": "It seems like we should leave `notice` here since it can be configured in Bolt config files, and that's what sets the console config for messages from Puppet. For example, this will break plans that call `notice()` in their apply blocks."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This metrics is only exposed in executors. Should it be defined in azkaban.execapp.ExecMetrics instead?"
    },
    {
      "prediction": "I don't think this is a good idea to use `moment.locale()` instead of `moment.locale()` and `moment.locale()` instead of `moment.locale()`",
      "reference": "I originally factored out these functions from date_input. Currently, they are only used in datepicker, but they seemed more general purpose. If you decide we should keep the current date_input API (in case anyone is using it directly), then I think it makes sense to factor these out in order to be able to maintain consistency, but otherwise they could be inlined into datepicker.jsx if you prefer."
    },
    {
      "prediction": "I think this should be the case where we want to use the `enumsspb.WORKFLOW_BACKOFF_TYPE_CRON_SCHEDULE` or `enumsspb.WORKFLOW_BACKOFF_TYPE_CRON_SCHEDULE` and `enumsspb.WORKFLOW_BACKOFF_TYPE_CRON_SCHEDULE` and `enumsspb.WORKFLOW_BACKOFF_TYPE_CRON_SCHEDULE` and `enumsspb.WORKFLOW",
      "reference": "I think this should never happen and should return an error also. Having `WorkflowBackoffTimerTask` with `UNSPECIFIED` type looks weird."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Add `browser` import"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would it be good practice to add a nonce in here (that's also stored in the config), so it's harder to tell when passwords are being reused?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "For consistency, the return type could be `TelemetryDataDto` here. This would be more consistent with the other REST API interfaces. From a functional perspective, the current code is perfectly fine though."
    },
    {
      "prediction": "This is a hack, but it's a hack, but it's a hack, but it's a hack, but I'm not sure if this is the case.",
      "reference": "I've never seen this `boost::make_shared`...why use it instead of `reset`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `getDispatchMethod(final ExecutableFlow flow)`?",
      "reference": "Wasn't this added as a part of different PR already?"
    },
    {
      "prediction": "I'm not sure if this is a string, but it's not a string.",
      "reference": "hmmmmm, should not be in constructor in this case `$this->toDelete = [[]];` ??? maybe not"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We can just update it to be as follows: `if response: print(\"Success\") else: print(\"Error\")`"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Maybe this should be exported so (external/third-party) plugins can also use it."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Warning logging whould be exactly here in high logic. So that everybody understands why we swallow errors"
    },
    {
      "prediction": "I think this should be a string?",
      "reference": "if its optional, move it to last item an use JsonRpcUrl? url = null"
    },
    {
      "prediction": "I'm not sure why this is a hack, but I'm not sure if this is the case.",
      "reference": "how is this different from the `client_slug` method already available on a `user` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd keep this at `info` level..."
    },
    {
      "prediction": "I'm not sure if `TRAVIS_FILTERED` is set.",
      "reference": "I believe this env var won't be set anywhere. Do we need this condition?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `window.getParameterByName(name, url)` or `window.getParameterByName(name, url)` or `window.getParameterByName(name, url)`?",
      "reference": "why add function explicitly?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is that intentional? If you don't create the cache here, it will never be created therefore used."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "I think we can now remove this test case since we can ensure that multiple calls to `Fetch` will double the interval on each call"
    },
    {
      "prediction": "I think this is a hack, but I think it's a hack.",
      "reference": "Not part of this PR but this const seems to be defined in multiple places. Needs to be extracted somewhere."
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case.",
      "reference": "Remove this file from the PR"
    },
    {
      "prediction": "I don't think this is the case for IstanbulBlockNumber < IstanbulBlockNumber.",
      "reference": "need to add it for ropsten, rinkeby, goerli as well"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "G204: Subprocess launching should be audited (from `gosec`)"
    },
    {
      "prediction": "I'm not sure why this is a static class, but it's not a static class, but it's not a static class, but it's not a static class.",
      "reference": "curious why only making these 3 public. what about other package scope methods like `times`, `timestamps`, `array`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "The Email field is not translated into Russian, and into any other. It's kind of a \"standard\" word. Therefore, we may face the fact that you have to create files with exceptions for all languages. @caouecs, what do you say?"
    },
    {
      "prediction": "This is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack, but it's a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "Should it say `default 0` here? looks a bit confusing. Also following BODMAS we should put: `2048 * (signature checker threads + 1)`"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Add a newline. We group by 1: standard library, 2: 3rd party library, 3: application library"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So `queryRange.Step` will be ignored?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "It would be nice to replace these _HOST_* defines with HOST_*."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "The problem here was that the record file started with something like `/tmp/whatever/myproj` and was scrubbed to `[ROOTDIR]/myproj`, but the `/` is a `\\` on Windows."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Don't use relative paths. src directory is already on the include search path"
    },
    {
      "prediction": "I'm not sure if this is the case for the test_cmd to be used.",
      "reference": "if we're introducing this now can we make this private?"
    },
    {
      "prediction": "I think this is a bug in the IonMobilityFinder.",
      "reference": "Something is wrong with the indentation here."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This should go to the external imports group below"
    },
    {
      "prediction": "I'm not sure why this is a good idea.",
      "reference": "Intended to be checked in?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think this warning message is the same as above one. Anyway, it's fine to keep it."
    },
    {
      "prediction": "I think this is a bug in Nethermind?",
      "reference": "This is done few times, replace with some well named method"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "`configs` isn't very descriptive, especially when there are other config-ish things like `generatorConfigs`."
    },
    {
      "prediction": "I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case. I'm not sure if this is a test case.",
      "reference": "In my point we have to check conversion with specific (non-ASCII) characters in unicode string."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Given that file still contains doctests (and should still contain doctests), they should be run. Please turn this back on."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "we should keep the camel case format - selfServe"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "consider the alias `compute` in case this ever references other apis."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "It probably doesn't matter in practice, but we're not supposed to access a map without holding a lock. This is why I have suggested using `m.Path(\"devices\")` earlier -- it takes a lock before accessing m.paths. Alternatively, you can leave this code as is but add taking a lock (same as `Path()`)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Since `ga` is an acronym here, we should rename the generated actions and selectors to adhere to our naming conventions as it will no longer be capitalized properly. See below for how this is already done for the amp container ID settings. We should add `GA` to our list of checked acronyms as well in `packages/eslint-plugin/rules/acronym-case.js`."
    },
    {
      "prediction": "I'm not sure why this.status.uploads.push(file) is the same as `this._fetchStatus({ diff: false })`",
      "reference": "uploading_finished and upload_meta_data_extracted can fire very quickly after another, and there is not much difference in the Assembly status that's useful to us. I kept only the Assembly fetch after metadata is extracted, which ensures that we'll have all the correct `uploads.*.meta` properties on the client side."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Does it make sense to keep trying to read the file every time the function is called, or should we maybe use `sync.Once()` here?"
    },
    {
      "prediction": "I think this should be a string, not a string.",
      "reference": "`DbCapacity` -> `DBCapacity`"
    },
    {
      "prediction": "I think this should be the same as the first block, but it's not the same as the first block, but it's not the first block.",
      "reference": "For Berlin I confirmed all the fork hashes with the Geth team. Would you do the same with Martin? He responded quickly the last time."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Does `sudo` required for `darwin` only? Don't we need it for `linux` too?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `aws-sdk-go/aws/session` and `aws-sdk-go/aws/session` and `aws-sdk-go/aws/session` and `aws-sdk-go/aws/session` and `aws-sdk-go/aws/session` and `aws-sdk-go/aws/session` and `aws-sdk-go/aws/session`",
      "reference": "Can you add description to this exported struct?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Although this is needed for `getSnapshotBeforeUpdate` this also fixes a bug with `componentDidUpdate`. During rendering, the `state` variable is mutated. This has the consequence, that `previousState` would never hold the previous state, but the most current one."
    },
    {
      "prediction": "I don't know how to import it from the service, but I don't know how to import it from the service.",
      "reference": "Should this maybe directly start with ELBv2 aka NLBs or ALBs?"
    },
    {
      "prediction": "I don't think this should be the case for the `google-site-kit/v1/core/site/data/notifications` and `google-site-kit/v1/core/site/data/notifications` and `google-site-kit/v1/core/site/data/notifications` and `google-site-kit/v1/core/site/data/notifications` and `google-site-kit/v1/core/site",
      "reference": "This was the request that was often causing the test to fail as an unexpected API failure (or at least one of them   )."
    },
    {
      "prediction": "I think this is a network error.",
      "reference": "I understand why `xhr = null`, but I think adding `error = null` implies that this method should work even if we don't pass the `error` argument. Should we remove it?"
    },
    {
      "prediction": "I think this is a bug in GrpcGrpcMethodConfig.",
      "reference": "It is not your code, and it is used like this all over the place in gapic generator, but the general rule is we should prefer using the least specific class/interface in the hierarchy, which still satisfies our requirements. Here, unless we really need anything specific from `ImmutableSet`, please use `Set` (less specific type) instead."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Sorry... I just realized... since we use sts_endpoint in the EKS Provider, this error message is no longer true. Role_arn is not required."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "(...), where each element ~are~ **is the** given {\\@code element}."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "I think this can be an int because we have a default that is always valid, `0`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but it's not the right thing to do.",
      "reference": "I think you can use `build_stubbed` here for the same results but with more speed."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "what if one of them is property and one is not?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "> UI plugins swallow rejection errors so they don't end up in the console with no way to fix But it will still catch upstream in `addFile` and restrictions to show the informer?..  "
    },
    {
      "prediction": "I don't think this is the right thing to do with the `session` argument.",
      "reference": "can't this just be left undefined/null?"
    },
    {
      "prediction": "I don't know how to handle this, but I don't know how to handle it.",
      "reference": "changed bc we are using the `error` var below"
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Is there a reason why this is change is in the same commit?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "@nghialv btw, perhaps was this method originally created for copying the repo root to the given `dest` as a subdirectory?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Just curious - why not var?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Why would we import this here and not use it? Is there a side-effect of this import?"
    },
    {
      "prediction": "I think this is a bug in RSpec.",
      "reference": "The name `errors` is a bit mis-leading -- usually I'd expect a field called `errors` to be an array of errors but here it's just a count. And it's not a count of _all_ errors -- it's a count only of some errors."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "there was no usage of the bundle in the framework? everything works exactly the same after the removal?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Why this difference?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Surround code issue. RequestError may not be null terminated when the RequestError size is less than the length of the string in p_buffer->errorText. Also, this can cause core dump due to segment violation if length of errorText is less than the size of RequestBuffer."
    },
    {
      "prediction": "I don't think this is a bit of a hack.",
      "reference": "`AccountMaxVersionPrefix` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `go.temporal.io/api/common/v1` and `go.temporal.io/api/enums/v1` and `go.temporal.io/api/namespace/v1`",
      "reference": "I see it is not part of this PR but I somehow overlooked it before. Can you use same import aliases as we use everywhere in the project: `apicommon` -> `commonpb` `apireplication` -> `replicationpb` `\"go.temporal.io/api/enums/v1\"` -> `enumspb \"go.temporal.io/api/enums/v1\"`"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "Nit: Maybe merge these into one string while you are here?"
    },
    {
      "prediction": "I'm not sure why this is a good idea.",
      "reference": "Why make a new file for this? I think keeping everything related to the scheduler in a single file increases readability. Especially when there is no API-boundary in between. Functions like `getCoroutine` and `yield` also live in the normal scheduler files so it doesn't seem consistent."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "tiniest of nits: why would you abbreviate \"interface\" but not \"configuration\" ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Removing since all of the domain-neutral testing will be done in the new `Samples.MultiDomainHost.Runner` app"
    },
    {
      "prediction": "I think this is a bug in Cygwin.",
      "reference": "is there a better way to detect this rather than just always assuming it's cygwin if everything else fails? i think you can check `if sys.platform == 'cygwin'`"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "duplicate code - can you move into build_from_path() ?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "  very important test as we want to make sure the old name still work."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "I think returning 1 should some how be moved in to specific support for LibreOffice.."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Should be inside `ifdef X86` I would think (or moved to ... I guess arch/x86/emit_utils.c)"
    },
    {
      "prediction": "I think this should be a list of valid edge nodes.",
      "reference": "Using sync.Map(key: nodename; value: state) instead of this \"EdgeNodes\" string slice here would be much better. Reasons: 1. Using sync.Map makes the time complexity of function UpdateEdgeNode and IsEdgeNode O(1), while using string slice with for loop makes it O(n). 2. Later we could be checking node state whether it's \"ready\" or still \"not ready\" by directly comparing \"value\" of sync.Map and doing the node state updating."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "nit, does it make sense to get this variables outside the func where they are used?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "to **an** Amazon... Simple Notification **Service** (singular)"
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "Nit: is \"top\" a short name we use frequently? Seems a bit mysterious, and saves only 2 chars."
    },
    {
      "prediction": "I don't think this is the default value for the protocol version.",
      "reference": "This name is really confusing. May be just remove this const completely and hardcode `4` where it is used?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why did you remove this spec?"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "The vendor prefix is still being used on Chromium based browsers like Edge Chromium and Chrome. Did you mean to remove this?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `composite_root_resources` parameter?",
      "reference": ".get will return None if there is no project_id key, so the or None part is redundant"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do they need to be `internal`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hit a flake here where I think there may have been some output to stderr that got mixed in with the output from Stdout. Hence switching to `Output()`, which does also capture stderr as `err.Stderr`"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Is there any official CUDA API called cuMemcpy2D_v2?"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Can you please move this interface as class in common Constants file in az-core module?"
    },
    {
      "prediction": "Should we remove this?",
      "reference": "Why not TempDir?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "IMvxFormsView -> IMvxElement is a breaking change, isn't it?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This should be imported alphabetically."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please apply same changes as for Payment"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `useSelect` or `useSelect`?",
      "reference": "This should only be used in the `ScrollEffect` component, as you have in the `DashboardMainApp` below  "
    },
    {
      "prediction": "I don't know why this is the case.",
      "reference": "I'd call it `g.auth_token`, just to make it more clear"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Not sure if this is what we really need, we might need to adjust this constant after more extensive benchmarking."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Shouldn't we use `:branchname` here? Or just `:branch`?"
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case. I'm not sure if this is the case.",
      "reference": "`AutoTime` is a number but calling `int()` would make it crash. Tested through the docs"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@eddynaka Looks like the same block more or less 4 times, should we have a helper method? private void AddOrReplaceAttribute or something?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Please do the same for the DebugFilter a few lines above."
    },
    {
      "prediction": "I think this should be the same as `act` and `setupRerender` and `setupRerender` are the same as `act` and `setupRerender` and `setupRerender` are the same as `setupRerender` and `setupRerender` and `setupRerender`",
      "reference": "Minor nit: Just inline both functions here. No need to make a file per function (that's a popular approach for some projects though, just not for us :) )."
    },
    {
      "prediction": "I'm not sure if this is the case where the default sources are used.",
      "reference": "There are several uses of the word \"default\" in here, perhaps it can be reworded slightly?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`function (` is correct. A space must be there. Please run `make cs` to have correct coding style."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think this is now going to fail the scenario where there is a `main` with aria-hidden=\"true\". I don't think that should fail."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this specifically that if we capture the cast in another variable, even if it passes escape analysis, that the runtime will copy?"
    },
    {
      "prediction": "I think this is the default value for `kmsAliasPrefix` and `kmsAliasPrefix` is the default value for `cluster-api-provider-aws-*`, which is the default value for `cluster-api-provider-aws-*`, which is the default value for `cluster-api-provider-aws-*`, which is `cluster-api-provider-aws-*`, which is `cluster-api-provider-aws-*`, which",
      "reference": "Should this be optional for existing configs to work?"
    },
    {
      "prediction": "I think this is a bug in the chequebook.Issue function.",
      "reference": "note that `balance` does not necessarily fit into `int64`, especially with the new bzz token. so you might want to avoid the `int64` conversion step using `big.NewFloat(0).SetInt(balance).Float64()`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "lets leave out the `-S` ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is this method needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How about, instead of reading the param every time, just add a class member variable to hold the value of the flag, and just set it once during `LayerSetUp`?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Does this mean it's only returning tasks associated with the primary deployment? or something else"
    },
    {
      "prediction": "I think this should be an error, but it's not a real error.",
      "reference": "nit, would be good to include prefix for this log statement."
    },
    {
      "prediction": "I think this should be a function, but it's not a function.",
      "reference": "Same here, you should use a made up role. May I suggest `role=\"McCheddarton\"`? :)"
    },
    {
      "prediction": "I think this is a bug in SparkWrite, but it's a bug in SparkWrite.",
      "reference": "@aokolnychyi, shouldn't this check whether the operation is a delete? If this is invoked by `DELETE FROM` then we don't need to validate conflicting deletes."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Any reason to split up this import block? I think most files have them together in one block, right?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`Tags.AppSecEnabled` should probably move to `Metrics.AppSecEnabled` I guess?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "What happens if you remove this? Can't you still initialize this atomic_file class, since it's just AtomicLocalFile with an additional method (move_to_final_destination)?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `link_to(t('layouts.partners_bytemark'), \"https://www.bytemark.co.uk/\")` and `link_to(t('layouts.partners_bytemark'), \"https://www.bytemark.co.uk\"), `link_to(t('layouts.partners_bytemark'), \"https://www.by",
      "reference": "As previously discussed in #1944 it's not safe to remove IC like this as it will break every language that still has a `%{ic}` marker in the translation."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I believe these rules will be enforced both (1) on egress from a local workload, and (2) on ingress **to** a local workload. Right? I understand that we definitely want (1), but do we really want to enforce (2) as well?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Update after command rename"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "What about adding an optional parameter that allows users to choose whether they want to use the format or not?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Lint didn't like this context being before the skip"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `http.Handler` and `http.ResponseWriter` and `http.Request`.",
      "reference": "so now basically anybody could drink my tequila? currently electron dev-env runs on `http://localhost:9080`"
    },
    {
      "prediction": "I think this is a bug in ILXQtPanelPlugin.",
      "reference": "`mPluginLoader` is nullptr in static plugins, which causes segmentation faults"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Better use `Optional<Consumer<String>> onSearch` here."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "this is asserted as invalid input"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "Why do you need to create a new parser? Can't you just use `state.Parser` to answer this question?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "remove processing references from Nethermind.Core where possible, keep clean"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Why not make this a subclass of `MessagingException` so we don't need to change all `throws` clause?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "it should instead be `from .hmac_drbg import DRBG` also, please put it at the bottom of the imports (PEP 8 order), so near line 36"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Nit: indentation is 2 indents (4 spaces) from the previous line."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't understand why this is changing to a hard-coded string."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: perhaps calling this `config` would be more clear?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I would rather recommend using 'Wird hochgeladen' since the imperative form of 'Lade hoch' confuses me whether this is an action I need to do or whether it's an action that Uppy is currently doing. Just my two cents."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Hmm I would have expected this to go away? What role does it play now that we have a minimum?"
    },
    {
      "prediction": "I think this is a bug in the spec.",
      "reference": "if we are removing this, is it useful to have the `isGetMoreError` message below? If that's not required, can we also remove the `mongoErrorContextSymbol` outright?"
    },
    {
      "prediction": "I'm not sure why this should be done in the future.",
      "reference": "I think this mutex is only used here. Remove it."
    },
    {
      "prediction": "I don't think this is the right thing to do, but it would be better to use `Thread.currentThread().interrupt()` instead of `Thread.currentThread().interrupt()`.",
      "reference": "it's unclear to me which method you are recommending overriding?"
    },
    {
      "prediction": "I don't think this is a bug in the code, but it's a bug in the code.",
      "reference": "This make me think that if the typing of a variable is inconsistent it could cause problem. For example here, if `field == 0`, the behavior is not exactly the same. A `0` and is implicitelty false. Well it works because summing 0 is neutral, but what if it was a multiplication ?"
    },
    {
      "prediction": "I don't think this is a bug in libopenstorage/openstorage/api/client.",
      "reference": "Remove this file from the PR"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I cannot find the changes / results of the eip2565 benchmark"
    },
    {
      "prediction": "I'm not sure why this is a `googlesitekit.moduleDataResetHandler`?",
      "reference": "@tofumatt now that I see this in context, we're now resetting 2/3 of the keys in the `NewComponent` state - the other being `error`. It seems that `error` should probably also be reset - essentially resetting all of the component state when the date range changes. What do you think? cc: @felixarntz @adamsilverstein"
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure if this is the case.",
      "reference": "This one and the ones below are for shutdowns but if it appears in some method called frequently during the lifetime of the process it should be cached in a static."
    },
    {
      "prediction": "I think this should be a function, but it's not a function.",
      "reference": "Better to just do `const err = yield User.bulkWrite(ops).then(() => null, err => err);` so you don't need to write out the whole `try/catch` block."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "`action.ExecutionDataGas = 100`"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "@supersmile2009 please review. Is it right to mark this as legacy? Are we testing the legacy path here? Are there tests for the non-legacy path?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "getSpcResource should not be bothered about deletion. Can we have `separation of concerns` for this logic?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is actually matched with pandas's result since the output is sorted."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "struct field tag `yaml:\"endpoint\"\"` not compatible with reflect.StructTag.Get: key:\"value\" pairs not separated by spaces (from `govet`)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This is not necessary. Topic inherits from DomainEntity which already has instance_handle_"
    },
    {
      "prediction": "I think this should be a test.",
      "reference": "Do we need the forXDP parameter in runBpfUnitTest? If not, I think better to revert in order to save a few changes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "All the code that reference to this function must also be changed."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How is this new interface different from existing `validateProxyUser` method? If I understand correctly the `proxyUser` parameter is essentially a group and the method should verify if `realUser` belongs to it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we have namespace conflicts?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We have several groups of caches so I think we should not use this shared configuration value for all of them. Instead of that, each cache group should have a separate configuration field, and the added `validation cache` should have its own field too. But this point, they can be fixed by `24h`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This is a BC break for extending classes, it can't be done on 3.x"
    },
    {
      "prediction": "I don't think this is the right thing to do with the server side encryption keys.",
      "reference": "Line length (PEP8, should be 80 chars max)"
    },
    {
      "prediction": "I don't think this is a bug in the code.",
      "reference": "this is duplicate now. I suggest moving it into `MimeHeader`, we already have a bunch of other headers there"
    },
    {
      "prediction": "I think this is a bug in rclone.",
      "reference": "Can you expand the warning slightly \"Your password contains leading/trailing whitespace - in previous versions of rclone this was stripped\" Just so users know they might have to type their password without a leading space."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I think \"this\" should be \"parent\"."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Why not init this at variable decl time instead?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do we still need this if we're doing everything through `envconfig`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I would like these options to have `experiment` prefix or suffix. Because we will be deleting them later"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Since we have the same logic in both forms, can we make a shared partial/helper for it?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Why to introduce this intermediate variable?"
    },
    {
      "prediction": "I don't think this is the default value for client_type.",
      "reference": "Maybe use ChoiceParameter?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `:show` or `:cancel_form`?",
      "reference": "Not positive is this is needed, given the `TokenAuth` include"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Why not use a docstring for it?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Two more tests - no ports specified and every possible port specified - p2pPort, graphQLHttpPort, rpcHttpPort, rpcWsPort, metricsPort, metricsPushPort, stratumPort"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Don't worry about that next time, it's automated :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "No need for this, as pylint already only turns things off for this function and it's needed for the entire function."
    },
    {
      "prediction": "I don't think this is the default value for `FLUENT_HOST` and `FLUENT_PORT`",
      "reference": "Are these values expected to change over time? Why not inject these values in ECS backend instead of agent doing it?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `node-name` option.",
      "reference": "as best i can tell, you are setting this here in order to make it available in `(e *ETCD) Snapshot(ctx context.Context, config *config.Control) error`. It feels wrong to pass state like this through an env var. Could you instead add a `nodeName` property to the ETCD struct?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "These seem to support the new test framework below, but the `.in.csv` files are still committed."
    },
    {
      "prediction": "I think this is a bug in Nethermind.",
      "reference": "!txReceipts[i].Removed and We can check it for first item outside of for loop, we don't expect mixed batches"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "We can't unfortunately change any of our old flags :( it'd be a breaking change. Instead, we can keep both `githubURLFlag` and `repoURLFlag` and make the description of `githubURLFlagDescription` as \"(Deprecated) Use --url instead. GitHub respository URL for your service.\" It would be even better if we can make `githubURLFlag` as hidden but keep in the command. This way old commands will still work with `--github-url` but it won't appear anymore in the help menu."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This provides file and line number if applicable."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This is already imported. Please check the file."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "One thing we can do in a follow up is use the shorthand calls, so You can just call `aSelection.unselect()` instead of calling the more verbose `execute()`. The fact that you have to check if the action is available sort of sucks though."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think adding this value to _every_ connection policy is needed or useful... why is this necessary?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I",
      "reference": "adding this constrain for null AggreagateId is redundant"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why when current user is owner but still check access? Should we use `else if` here?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "60 seems high. 10? 20?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I think this is not the best way to handle this problem. This way every relative path will be converted to absolute path. What if the user would like to move his config directory to a different directory?"
    },
    {
      "prediction": "I don't think this is the default, but it's the default.",
      "reference": "Let's make this a pointer given that's optional"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `require('stream').Stream` or `require('stream').Stream` or `require('stream').Stream` or `require('stream').Stream`?",
      "reference": "Why is CircularJSON imported here? It is never used in this file."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Should be ARM"
    },
    {
      "prediction": "I don't think it's a directory, but it's not a file, but it's not a directory.",
      "reference": "I don't see how removing \"open file bucket\" helps your purpose."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Solr dependency was downgraded?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `config.autoload_paths` property.",
      "reference": "or should we just autoload everything in `lib` ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Prefer `Stream.anyMatch` instead of iterating over all slots."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `INSERT_VIOLATIONS_TABLE`?",
      "reference": "create_tables isn't used in 2.0 (should probably be deleted?)"
    },
    {
      "prediction": "I don't think this should be used in the future.",
      "reference": "Now I start to wonder, do we want to have `80` as the default or `9090` (or depending on whether we are exposing it via `PrometheusExporterMiddleware` vs. `PrometheusExporterHttpServer`)?"
    },
    {
      "prediction": "I think this is a bug in GQL, but it's a bug in GQL, but it's a bug in GQL, but it's a bug in GQL, but it's a bug in GQL.",
      "reference": "try an illegal case. and the result is syntax error."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Initialize `needs_reshape_` with true and call `Reshape` method"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is a _very_ complicated line. I'm not a fan of ternaries to begin with (although, I allow them in very simple situations), but this ternary has compound conditionals and would really need to be broken up. That said: if I'm reading this right, it sounds like this logic can make it where this lambda (which is called `RANDOM_ORDERING`) can make it not random and basically do the opposite of what it says. In general, it's good to avoid making methods or lambdas do the opposite of what they say."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "We should remove this"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should validate this, I think. To add a validator: - change `string` to, say `iface-pattern` - add a new `case \"iface-pattern\"` to the `switch` in the `loadParams()` function: - in that `case`, you should be able to use a RegexpPattern like the one for `iface-list`. However, you'll need a different regexp. I think this regexp should work: `^[a-zA-Z0-9:._+-]{1,15}$` i.e. 1-15 characters consisting of alphanumerics, colon, dot, underscore, hyphen and plus."
    },
    {
      "prediction": "I think this should be the same as `SubBalance`?",
      "reference": "File is not `goimports`-ed with -local github.com/iotexproject/iotex-core (from `goimports`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: Here we don't need the extra `this` in iceberg because we usually use the `this` to distinguish whether it is a member variable or local variable when assigning value."
    },
    {
      "prediction": "I think this should be a problem?",
      "reference": "Why do we have that extra \"ENGINE-16002 Exception while closing command context:\" now? Is that done intentionally by us or where does that now come from?"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Please don't use star imports, in the codebase we tend to use direct imports."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Filename can be `config.functional`"
    },
    {
      "prediction": "I don't think this is a thread, but it's not a thread.",
      "reference": "Should the thread join be done in the stop function maybe? I am simply wondering and sharing my thoughts. This is my thinking: * The join used to be done in the stop function of node class and now it has moved in the destructor. * The class state_block_signature_verification joins its thread at the stop function too."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "don't use `init` function (from `gochecknoinits`)"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Simple Notification **Service** (singular)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You are fixing the crash problem, and you have fixed it, so it won't crash anymore. So `crash_test` is not a proper name."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "If this default doesn't depend on the argument, shouldn't it be delegated as the default for the no-arg version instead?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I did not use the new save_config_file method in here, because I am not sure whether this whole logic is still necessary? There is an TODO about it there as well."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why was this changed?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I think you meant, self.floor_thr = 0"
    },
    {
      "prediction": "I don't think this is a bug in the GQL parser.",
      "reference": "Can you revert these changes?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with React.",
      "reference": "Do we need to change this?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "With this commit, `MemoryUnlimited` is defined as a `unit64`, so I think you can drop the redundant cast from this line (and the later lines which also have `uint64(configs.MemoryUnlimited)`."
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function, but it's not a function.",
      "reference": "`props.totalFileCount < props.maxNumberOfFiles` makes the intent a bit more clear I think. And a check to see if maxNumberOfFiles even exists?"
    },
    {
      "prediction": "I don't think it's a bit of a hack.",
      "reference": "`epochNum` is a global variable (from `gochecknoglobals`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This needs to be fixed before we can accept the PR"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Are these forward declarations needed if we `#include <node/common.hpp>` which includes the definition ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can you use either `connectID` or `ConnectID` i would preffer `connectID`"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "It seems like it cannot be null?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "should we consider add deprecated annotation here?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `libkbfs.ConfigLocal` and `libkbfs.ConfigLocal` and `libkbfs.ConfigLocal`?",
      "reference": "Why can't the implementor get the username from the config?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@CoderZhi Please confirm if this change makes sense"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Do you think you can come up with a better message? :-) It looks like this is not used anywhere. So maybe just delete the line."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `reduceLeft` method.",
      "reference": "`tail()` is an expensive operation for certain collections"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "do we need to add this one in this PR?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "where is a test for it?"
    },
    {
      "prediction": "I'm not sure why this is the right thing.",
      "reference": "Why has this spacing been adjusted?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Sorry to do this, since you're touching this file can you resolve the pylint doc messages above?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `recording_msid` field?",
      "reference": "@alastair, because the `insertId` for two listens with different metadata and same ts was the same, only one of them would get written into BQ. A question is what would be the ideal way to write tests for stuff like this, so that this doesn't break again?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Wondering where this breaks btw (although pretty understandable)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "is this needed? 10 is already the default"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "One day we can try to allow the user to specify font sizes in something other than points. For now this is fine though..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "duplicated in both block of preprocessor condition. Can you join in one?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can we put the first part of the expression inline with the `if(` for consistency's sake?"
    },
    {
      "prediction": "I think this is a bug in YARPC-go.",
      "reference": "Do servers have no need of accessing this information?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `formatTimeAgo` method.",
      "reference": "It feels like this will break some stuff, but let it break. We need \"text\" version anyway."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Here are two things I wonder: First, would it make sense to replace the TRUE here with \"leftExpr->getValueId().getType().supportsSQLnull() && rightExpr->getValueId().getType().supportsSQLnull()\". I'm not sure we have optimizations elsewhere that set the \"special nulls\" semantics back to FALSE if one of the operands it not nullable. Second, I wonder whether we have bugs elsewhere in the code that may not check for the \"special nulls\" semantics. For example, hash and merge joins probably can't use such predicates as equi-join predicates - one of the reasons for the optimization above. When I look at method ItemExpr::isAnEquiJoinPredicate() in core/sql/optimizer/OptItemExpr.cpp, I don't see a check for that. You have an example with a NULL value that is working, so hopefully this is not an issue, but I'm not sure how and why it works."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This will cause someone writing a schema field like `inf:string` to get a pretty confusing error? If they intended to use `inf` as short for `information` or whatever :) Might it be better to keep it as `Identifier` and explicitly recognize the few identifiers we care about only when parsing values (not while parsing field names)?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `jwt.sign()` instead of `jwt.sign(payload, secret, options)`",
      "reference": "Mmm .... this affect #168 I'll need to research the collateral damage"
    },
    {
      "prediction": "I think this is not a good idea.",
      "reference": "nit: refactor into a const map lookup."
    },
    {
      "prediction": "I don't know why this is the resource assembly?",
      "reference": "I don't think this is going to work. We need to get the actual assembly of the app project. @johnnywebb thoughts?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "@MSusik be careful about changing existing API. I think in this case you shouldn't rename the argument."
    },
    {
      "prediction": "I don't think this is the case where the default topic is not set for this message.",
      "reference": "This is bad. It is not a NULL-terminated string here."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "This probably should be @param string|false."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Unrelated test fix. Already in cordova34 branch."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `validate` method.",
      "reference": "validate() will be called by either V1 or V2"
    },
    {
      "prediction": "I think this is a bug in CppGenerator.",
      "reference": "rather than generate code for this every time, stick it in `flatbuffers.h` (and call it `FLATBUFFERS_NOEXCEPT` to avoid clashes)."
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "@AskAlexSharov @tjayrush , I'm still feeling uncomfortable with this change: - because it works by accident. For example in next lines `tx` object used as: `ReadBlockByNumber(tx)`. If you go inside `ReadBlockByNumber` you can find `!errors.Is(err, ethdb.ErrKeyNotFound)` - but ethdb.Tx doesn't return this error - and it satisfy `DatabaseReader` by accident - (I faced this problem last week - when passed Tx to place which expected Db - and I promised to change tx API - rename Get to GetOne or even remove the method). - we can merge this PR if it doesn't break things and solve problem of localDb use of RPCDaemon. But I will make PR now which will allow open Read tx by TxDb/ObjectDb - and will ask you to use it. Then will take a look how hard to change LmdbTx to not satisfy rawdb.DatabaseReader interface."
    },
    {
      "prediction": "I don't think this is the default behavior for anomaly mode.",
      "reference": "I think this means the file doesn't have a newline character at the end."
    },
    {
      "prediction": "I don't think this is the case, but it's not the case.",
      "reference": "Hi Ramya, rather than checking here in the perf counter library, we should add the privilege check in the host_exerciser app."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Could you elaborate on this some more? Has this behavior changed with Python 3.8?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we want to continue on logging the `dumpedBody`, if an error was thrown? It is probably an empty string. This would make the log after this one pretty much useless."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "the text here is derived from the object type and not getting properly handled by get text"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This will make other pods that run antctl will also connect its localhost? Maybe only do it when it's in antrea-agent and antrea-controller"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the actionsheet.",
      "reference": "The corresponding action for this key needs to be removed as well, along with any unused translations."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `scope?.Span?.Context` and `scope?.Span?.Context` and `scope?.Span?.Context`?",
      "reference": "Can't Span cannot be null anymore? I assume it was a useless check as there are discrepencies within integrations, but as you explicitly removed this one, I was wondering"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "hmmm, ok, this is interesting -> Lukasz definitely uses rewards traces"
    },
    {
      "prediction": "I think this is the default value for this property, but it's the default value for this property.",
      "reference": "Why do we need this flag? can this be detected if the table is bucketed/partitioned and enabled/disabled automatically? Is this for backwards compatibility?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "can you revert changes to this file."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "suggestion to add: An soc is a chunks whose address is derived of (...)"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea, but it's not a good idea, but it's not a good idea.",
      "reference": "It doesn't make sense. if we are going to have the profile page where the user can change the password and he / she is already logged in ... I do not need to register a new username. only: new password..confirm new password..something similar...and \"USERNAME_ALREADY_REGISTERED\" only if I have a register page..are we going to have? We need to talk about it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "not a great fan of this change - maybe worth splitting into CommitTree() and CloseBlock(long blockNumber)?"
    },
    {
      "prediction": "I don't think this should be a method of `CancellationTokenSource`.",
      "reference": "Ugh, if we're going to make a breaking change, I'd like this to be moved to ConnectionContext."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I was planning to add it as a common option, but there is a cyclic import for the rc & fs libs. Thoughts on avoiding it or should I remove this for now?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think this entry can be removed now, right?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I don't understand why you want to populate the storage class in this case, if the S3 docs say they won't populate the header in this case?"
    },
    {
      "prediction": "I don't think this is a string, but it's not a string.",
      "reference": "These are really meant to be the keys in the capabilities, not the keys of values within the capabilities"
    },
    {
      "prediction": "The regionHint parameter should be an empty string.",
      "reference": "Should the last sentence be `If no region was found` rather than `specified`?"
    },
    {
      "prediction": "I think this is a bug in CoxPlugin.",
      "reference": "Text.sanitize just removes images from names, for instance, the hardcore ironman symbol when someone talks. A better option would be text.standardize, or text.toJagexName"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "How about `ApplicationKindFromConfigKind`? And I think this function should be better in the config package. The reason is `config` package can import and refer things from the model package but not vice versa."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Nit: missing closing \".\"."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe it's misleading name for the condition. I prefer \"element_to_be_disable\" We can have a condition, when element is enabled but we can't click it, because another element overlays above it. So, If we use \"unclickable\" we might mislead people, who use that condition to verify if element can be clicked"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Same here. Should this be pipeline YAML file? Like `MarshalPipelineManifest`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I will add this to my PR  "
    },
    {
      "prediction": "I don't think this is the right thing to do with the user.id?",
      "reference": "Again not 100% sold on the name"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `/user/settings` command.",
      "reference": "Use `m.Combo` for `Get` and `Post` methods."
    },
    {
      "prediction": "I don't think this is a special file.",
      "reference": "Is there a reason you're not using `self._die(\"The file {} ...\")` here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `exec` command.",
      "reference": "I think we'll want @rickmanelius (or somebody) to go through all the help and make it more accessible. Probably later in the cycle. But \"Run a command in an app container\" doesn't do it for me :)"
    },
    {
      "prediction": "I don't think we need to use the `--local` option, but we don't want the `--local` option.",
      "reference": "shouldn't this be a const?"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "This is a bit of a throwaway field in the xunit output, it doesn't impact anything on EVG, should we just name it `integration` now?"
    },
    {
      "prediction": "I'm not sure if this is a thread-safe interface, but I'm not sure if this is a thread-safe interface.",
      "reference": "Please change the name of the file too."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "line is 161 characters (from `lll`)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "When is this false?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "note: also here ;)"
    },
    {
      "prediction": "I don't think this is a good idea to remove the shutdown hook.",
      "reference": "I don't think we need to necessarily check if that returned true or not, we should just remove the shutdown hook. Since nothing would check or do anything with this flag anyways."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `git repo` or `local repo`.",
      "reference": "nit: blank between, for consistency."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "ditto for RDoc or YARD link"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This method is designed to allow the condition runner to tell users something interesting. The current `INFO` log level is correct."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Again, would not change that."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is canceled considered failed?"
    },
    {
      "prediction": "I think this is a bug in the tests.",
      "reference": "These ineffectual assignment changes intrigue me. Our CI tests have been checking for these for months; how come the tests haven't been failing? How did you catch these?"
    },
    {
      "prediction": "I think this should be a test case.",
      "reference": "We should add an additional call to Recv() somewhere after here that we assert returns io.EOF."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why not return a `ctx` from `setupJournalBlockServerTest` and use it everywhere, like in the other test files? And maybe put a test timeout on it while you're at it? (Same for the other journal test files below.)"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Do we need HeadlessSurface and DisplayPlaneSurface here too?"
    },
    {
      "prediction": "I think this should be a problem?",
      "reference": "Would it be appropriate for this to be a `MongoStreamClosedError`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can you raise new issue that talks about refactoring webhook code. It should follow `idiomatic maya` patterns."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "(Probably repeating myself) Instead of `Datadog.Trace.Interfaces`, should we move this and several other files into a `Datadog.Trace.Decorators` namespace instead?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should we generate `gem \"rsolr\"` into the application Gemfile?"
    },
    {
      "prediction": "I think this is a bug in flux-job.",
      "reference": "commit message, \"currently ignored\"? (-ed)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `page_ranges` option.",
      "reference": "Same here. and all others."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can we pass some simple interface instead of a full additional processor? (an imterface with these two events only)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Use a named constant"
    },
    {
      "prediction": "I think this should be removed in a future release.",
      "reference": "The `?` is unnecessary since `Assert.Single` will fail if it can't find the stop event."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "What about providers that don't have a reliable location? Do they return null?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `GetMetricFunction` and `GetAggregatedMetrics` functions.",
      "reference": "I might not be thinking about things right, but would it make sense for a MetricProcessor to have a handle on the ParentProvider kinda like how we do for traces? That way instead of calling `SetGetMetricFunction(this.Collect)` in the MeterProviderSdk you'd have a handle on the provider to call `Collect` directly."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: If we want to squeeze out a few more milliseconds from the startup, we may actually be able to remove this line (`wait_for_port_open(PORT_DYNAMODB_BACKEND, http_path=\"/\", ...` should already be sufficient to ensure that the service is up and responding to HTTP requests). Thoughts?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Convention is to use TEST"
    },
    {
      "prediction": "I'm not sure if this is the right thing to test.",
      "reference": "Just in case: remember to remove this."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I am not certain if this should be 0 or 7 here. I think a basefee under 7 is pathological"
    },
    {
      "prediction": "I don't think this is the case. I don't think this is the case.",
      "reference": "it would be better to move the declaration of the variable with its initialization at line 68"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "I don't think this is required."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This rename should also ideally be in a separate PR."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Think this needs to go right below line 91. `parseResponse` can return `null` (line 133), which will cause this future to never complete."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "Can you please revert changes to files in the `thoughtworks` package? This is legacy code and we will eventually phase out RC."
    },
    {
      "prediction": "I'm not sure if this.props.containsKey(ConfigurationKeys.ENABLE_QUARTZ) && this.props.getBoolean(ConfigurationKeys.ENABLE_QUARTZ, false)",
      "reference": "Yeah, why not use this method instead of checking with `containsKey`?"
    },
    {
      "prediction": "I don't think it's a good idea to do this, but I don't think it's a good idea.",
      "reference": "Compute `(time_forward + 1e-3) * 1e3 / loop_num` ahead."
    },
    {
      "prediction": "I'm not sure why this is a bug in the future.",
      "reference": "Mh... `MustBeRethrown()` above already logs `ex`, so `ex` will be logged here for the second time. I think this line must be moved to before `MustBeRethrown()`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Since this never changes, why not pass it into the constructor instead?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `_writeThrough` and `_targetDbForSaves` methods.",
      "reference": "this is critical to avoid state root saving from beam"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "To make it more clear, `fill=self.num_classes`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nit: \"ByteSize estimates the size in bytes of the message for the purpose of restricting batch sizes.\""
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It's weird to have this on the same level as kestrel. This needs to move to options."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `type` attribute.",
      "reference": "is it safe for us to use the `blob.type?.length` optional chaining with IE11 support? @goto-bus-stop"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "remove this debug statement"
    },
    {
      "prediction": "I don't think this is the case for the YCbCr extension.",
      "reference": "This should not be needed. 1) all 1.1 promoted extensions are marked as enabled when a 1.1 device is created (which happens iff both physical device support and apiVersion are set to 1.1) 2) The KHR and non-KHR versions of the bits are aliases of each other, so no different set is required."
    },
    {
      "prediction": "I don't think this is a bug in CCTOOLS_LOOP_DEV_FULL.",
      "reference": "I can see why you did it this way, but let's not get into the habit of passing information back via an environment variable. Add an element to `batch_job_info` instead, which is where we send back detailed info about jobs."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Turns out my previous fix of doing `!dom.hasAttribute('value')` is not a good one as it leads to all input values always being updated. The new fix only updates it, despite `dom.value === props.value` when the value is `0` for progress elements."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why is this being added here? Is this relevant to these changes?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This informational message is important to users. Please leave."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "why isn't rubocop failing for single quotes?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Is `WHERE` should `Language` param ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "ps - first letter from preview, when we move it into public it will not be relevant. my suggestion is spmd or ds(distributed)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Hm, should we show pandas' dtype instead of Spark data type?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `HistogramWithBuckets` and `HistogramWithMinMaxAndBuckets` or `HistogramWithMinMaxAndBuckets`?",
      "reference": "@reyang when exponentialhistogram arrives, we won't have any bits left for it.. unless we take Summary or make this 16 bits instead of current 8 bytes"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "This change is not tested.. I guess this is how these taint-annotations work..?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Fails if obj is list. Please fix!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could you add an assertion to make sure the `IncludeAllInstances` parameter is actually set and passed to the request?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The name of this argument is not too intuitive. The point is, these kind of subprocess calls will return `str`s in Python2 and 'byte`s in Python3. It would be a lot of work to make CodeChecker handle both `str` and `byte` everywhere. Using the `universal_newlines` argument, we can force Python3 to return text rather then bytes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "These `Get`s are just cosmetic changes for consistency."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We should never skip unit tests, but instead fix them. Look at `pytest.raises` for cases where we expect an exception."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure how to do this?",
      "reference": "Do we need to call ToList here?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I think this can be moved into the model, at the very least, but I also think you might be able to do a has many through."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "could you please separate computations from string concatenation?"
    },
    {
      "prediction": "I think this should be removed in 2.0.",
      "reference": "@NiklasGustafsson - I had to make these changes for the x-ms-client-name extension tests for java and python. The tests were expecting wire format instead of the client name. Hence modified them appropriately. Let me know what you think ?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Could we just set the list of header modification commands to `req->overrides` and apply them only when the request is sent upstream in lib/core/proxy.c? The reason I ask is because an upstream server (accessed using the modified headers) might return 399. In such case, the request would be delegated to the next handler. I think that the headers of the original request should be passed to the next handler, since per my understanding the intended behavior of `proxy.header.*` is to modify the headers passed to the upstream server only."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Can we rename 'refresh' to 'read' and 'update' to 'write'? Until I had read more of the code below, I couldn't tell the difference between 'update' and 'refresh'."
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "can we remove it ?"
    },
    {
      "prediction": "I don't think this is a bug in the code, but I don't think it's a bug in the code.",
      "reference": "I take it that by the time we get here, colName has already been case-shifted to upper case?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Super clear desc - thx."
    },
    {
      "prediction": "I don't think this is the case for all visible modules.",
      "reference": "Ahh the correct fix is to call `collectLinkLibraries` on the SourceFile being compiled, not the module. Sorry for our mistake!"
    },
    {
      "prediction": "I think this is a bug in the tests.",
      "reference": "Can you also modify the `TestEnvironmentConfig` in `config_test.go` to cover this?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "There's no point \"deprecating\" this interface method (the customer still has to implement the new callback that we have introduced which makes it a breaking change). I'd make an exception and simply rename it to `onResponse`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We chose `info` in the test code for obvious reasons. Changing to `finest` makes debugging harder and noisier."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I know this is not new here but we need to remove this global or protect access from multiple threads."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `configureHttpClientInstrumentationOptions` parameter.",
      "reference": "Doesn't seem any less confusing or error-prone to me. IMO the solution is to not use \"object\" in the enrich callback signatures. Type safety/compile-time checking is our friend!"
    },
    {
      "prediction": "I'm not sure how to do this with `-z $GOMAXPROCS`?",
      "reference": "I think this should be `GOMAXPROCS=$(nproc 2>/dev/null || echo 2)`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we log if this actually happens."
    },
    {
      "prediction": "I don't think it's a valid host, but I'm not sure if it's a valid host.",
      "reference": "This is not really needed, the line added in `GridNodeConfiguration.java` is what really fixes the `remoteHost` regression."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It looks like the import format was only changed from one-per-line to all on one line here. Can we keep it as it was so it's easier to see what changed? It's also more consistent with how we format multiple imports in other components."
    },
    {
      "prediction": "I think this is a bug in Selenium.",
      "reference": "Maybe call it `WireBridge`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Looks like `org.json.*` can be removed?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `GauntletTimer.CONTAINER` and `GauntletMap.CONTAINER` and `GauntletMap.CONTAINER` and `GauntletMap.CONTAINER` and `GauntletMap.CONTAINER`.",
      "reference": "remove the extra comma and newline"
    },
    {
      "prediction": "I don't think it's a page title, but it's not a page title, but it's not a page title.",
      "reference": "Can we try to use Ruby 1.9-style hashes?"
    },
    {
      "prediction": "I think this is a bug in Caddyfile.",
      "reference": "Terminology question - these are called \"global options\" in the code, but the parallel non-global versions of these are called \"directives\"... Should this be `RegisterGlobalDirective`? Or does that have different semantics?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I do not care much, but you could as well just return bool(focusObject and focusObject.isProtected) here and avoid the if check? I know, really trivial."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe it's misleading name for the condition. I prefer \"element_to_be_disable\" We can have a condition, when element is enabled but we can't click it, because another element overlays above it. So, If we use \"unclickable\" we might mislead people, who use that condition to verify if element can be clicked"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do DiscoveryContext and GoGapicContext have a more specific common ancestor than Object? If so, let's use that."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "is this the intended behavior now?"
    },
    {
      "prediction": "IJ should be a string, but IJ should be a string, but IJ should be a string, but IJ should be a string.",
      "reference": "Hunspell/C++ stems that a bit differently from Lucene, but in a controversial way, so I removed the check instead of changing the expectation"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm curious why this is needed?"
    },
    {
      "prediction": "Should we add a distanceEffect to the target?",
      "reference": "I do not see how that changes anything, as the target is operated on many times before that line?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Same user/visitor thing."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This is not the correct path on all hosts. How can I correctly determine whether I will need to look in `Program Files` or `Program Files (x86)` for the script?"
    },
    {
      "prediction": "I think this should be a `await` method, but it's not a `await` method.",
      "reference": "I think it would be better to move this try/catch block inside of the `FlushAsyncInternal` function as there are a few of places that can call it, eg event timer (here), AppendAsync, FlushAsync and CloseAsync."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "should we set a smaller initial size to make sure that we exercise the growing logic in our tests?"
    },
    {
      "prediction": "I think this is the same as `dt.sum(f[:]) == str(f[:].sum())`?",
      "reference": "Let's add a new line at the end of this file, so that the last line becomes a valid line of code."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why was this removed?"
    },
    {
      "prediction": "I'm not sure if this is the default value for `LogFilePath`?",
      "reference": "I would prefer that this tool follow the driver framework conventions, which use OutputFilePath as an argument, take a look at AnalyzeCommandBase. You can propose changes to that if you'd like, but binskim, sqlskim, this tool should all conform (in the interests of building an eco-system with consistent command-line interface)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "(...), where each element ~are~ **is the** given {@code element}."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "What if `AddOpenTelemetryTracing` is called multiple times?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is the condition of \"lastId <= wal _-> lastLogId() \" added here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "`environmentID` is unused in MakeEnvironmentURL"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the textView.setText(getString(R.string.null_search_result) + \" \" + '\"' + result + '\"');",
      "reference": "Just hide the textview"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "'Supports'? Very uninformative naming inside protocol. Why not just paymentVersion, or just recognise supported payment version from generic protocol version supported by the client."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should add an additional call to Recv() somewhere after here that we assert returns io.EOF."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "What is this used for?"
    },
    {
      "prediction": "I think this is a bug in the source code.",
      "reference": "this is a breaking API change. Do we really need to do it in 6.2.0? Can't we just deprecate the methods?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is dropping the **Allergen table** necessary? Can't we just add the two new columns to the existing table using a raw query?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'm confused why the expectations here would have inverted? Seems unrelated to topic stuff. Can you clarify?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I am very sorry that I neglected to resolve the conflict and did not fully unit test edge"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think closeable should be handled by the concrete impl of a catalog and not by the base class, I don't think all catalogs must implement closeable by design. This should be done via composition rather than inheritance. Additionally, I don't know what the effect of this change is on other catalogs so this feels a bit on the risky side."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "Should this be `const`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Can we also add the Exporters here by using `DefaultConfig.AddExporter(...)`? At least the Datadog exporter that can't be configured from the command line..."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "@JaeseungYeom I believe you had set this in a previous commit to, by default, not train model1 when loading from ckpt. Would it work for you to have this as a command line option `--no_model1_train` instead of the default behavior?"
    },
    {
      "prediction": "Is this a real Ruby type?",
      "reference": "@devigned, please clarify"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "File is not `gofmt`-ed with `-s` (from `gofmt`)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Should we break this up into a separate line?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why the override on the env variable, wouldn't we want to use the value set from Prow?"
    },
    {
      "prediction": "I don't think this is the default value for `projected_monthly_revenue`",
      "reference": "I don't see anything here that excludes people on a Team plan from from the revenue report. I see that TeamPlans are counted below, but the individual subscribers on the plan would still be included."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I know that we do not pull the last bit of performance out of the JVM but it is more robust and removes redundant code."
    },
    {
      "prediction": "I think this should be an abstract class?",
      "reference": "I'd make this a `throw new NullPointerException(\"registry == null\");` instead"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does adding things here require us also to extend the FelixConfiguration resource in libcalico-go?"
    },
    {
      "prediction": "I don't think this is a bug in the code.",
      "reference": "does this need to be public?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Please import this from a pre-existing definition."
    },
    {
      "prediction": "I don't think it's a bug in Mitmweb, but I don't think it's a bug in Mitmweb.",
      "reference": "File name does not represent class name... if we ever cared for such things?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "I don't mind the `make_spammer` route name. It seems to more clearly convey that the state of the account will change. The \"label as\" route name seems less definitive, as if one is simply adding something to the account -- a new label -- instead of changing the status of the account."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This exits if `-d` not specified which isn't exactly what we want, right?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `escape_char` parameter.",
      "reference": "So a `*` becomes `**`? How does this affect the query? If I have `csordas*marton` as filter and I have `csordas*marton` and `csordasFOOBARmarton` as run names in the database I get only the first as result?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "I want to know in which situation you need to traverse from \"Timestamp\" data....."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: hasBytes should be hashBytes"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "If I enable the clangsa analyzer with the `--stats` flag the checkers will be disabled even if they were enabled previously. I think we should check here if stats was enabled. `if 'stats_enabled' in args and args.stats_enabled` we should leave them enabled."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Note that we probably should set the default gasPrice to `0.1 gwei` considering our minimum gas limit has to be 21k. At 21k the minimum fee would end up being `0.000021 ETH` which is just a little too high"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "So during a config reload, this function is invoked, but prior to that the o.TrustedKeys slice is set to nil, so this code would work. However, I am wondering what happens to s.trustedKeys, I am not sure this is handled at all. (same with the new map you are adding). I am not sure if this is supposed to be supported with a config reload, but just wondering if this is not putting things into a bad state."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I think the logic should be to check for token len of 0 then check for token len of less than 2. The way the logic is now, it is hard to determine if it is empty or malformed."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Nothing would change here even if this `if` statement were removed."
    },
    {
      "prediction": "I think this is a bug in pyspark.",
      "reference": "`sql` module is imported later."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think it's strange, whether `assert cfg.nms.type == 'nms'` would be better."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Doing a quick search, it looks like there are other places that would be handling this promise rejection. How did you confirm this is not needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "let's use greenland in the unit tests as well"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Please split this into two lines"
    },
    {
      "prediction": "I think this is a bug in MVVMCross.Platform.Tvos.Views.ShowChildView.",
      "reference": "Is there any variable available instead of hardcoding 5?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here, but I'm not sure if this is the right thing to do.",
      "reference": "The onNewPasscode method was taking care of creating the user account. Now the user account will already have been created."
    },
    {
      "prediction": "I don't think this is the default value for `time.Millisecond`",
      "reference": "This is really a minimum, isn't it, so `minPostWriteInterval` perhaps? IIUC it never gets used as a default, because the default IptablesPostWriteCheckInterval is 1s, which is larger than this."
    },
    {
      "prediction": "I don't think this is the right thing to do, but it's not the right thing to do.",
      "reference": "I wonder if you can use the controller's context instead of using it explicitly?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you add this log for `baseline` too?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Let's call this \"NEW_BROADCAST_MESSAGE\". Msg.NEW_MESSAGE will be confusing down the line."
    },
    {
      "prediction": "I'm not sure if this is a transition dependency, but it's not a transition dependency.",
      "reference": "A better way to do this (in your future PR) would be to: 1. get rid of `TransitionDependencySet` altogether 2. tag `TransitionDependenciesMap` as `\"TransitionDependencySet\"` in JSON 3. update the JSON marshaler to deal with `\"TransitionDependencySet\"` tag. If it's a map, no big deal. Else, construct the `TransitionDependenciesMap` map. Doing that would mean that we don't need to have duplicate code, names for this."
    },
    {
      "prediction": "I don't think this is the case for a non-null logical_key.",
      "reference": "It's very error-prone to have so large `try` clause with such non-specific exceptions handled. Consider rewriting it with either of these: 1. Check that expected columns are present in `DataFrame` (`{'physical_key', 'logical_key', 'size'}.issubset(df.columns)`). 2. Normalizing output of query by using `COALESCE()` (or normalizing `DataFrame` itself?). Also it looks like a row with package metadata isn't used here, so might make sense to filter out it with `WHERE logical_key IS NOT MISSING`."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Change to `DisableHTTPGit`"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "org was not used in the mail content"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `light` and `dark` and `light` are the right thing to do with `light` and `dark` and `light`",
      "reference": "Is this gonna cause a lint issue, because of unused var? Maybe we should log it out?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "My understanding is that this will always be set to the actual containers IP, and never to the `DOCKER_HOST` IP if that env_var is set."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `setInProgress` method.",
      "reference": "this dependency to a callback also has to be a callback (eslint now warns us)"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "directory name as well needs change.."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Why is the getIdentifier() call required here?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Looks more appropriate to stick this in `AbsolutePath`.. actually that already has `FLATBUFFERS_NO_ABSOLUTE_PATH_RESOLUTION`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `hyperx(h)`?",
      "reference": "this might interfere when we have multiple dashboards. maybe ActionBrowseTagline needs to be a Component so we can store the reference to the element on it."
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "Should this be inside the `else` below and right after `CDebugf` so that we still get the logs?"
    },
    {
      "prediction": "I'm not sure why this is a problem? I'm not sure why this is a problem?",
      "reference": "Weird they don't expose the type for dynamo and this seems a pretty common error."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "@cijothomas I couldn't make the unit tests work without a way to destroy the ActivityListener we create internally so I return it as an IDisposable here. But we'll also need to also stop any ActivityProcessors/ActivityExporters on application shutdown right?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The default should be \"False\", as \"True\" would be a significant change in behaviour."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "since goal is to restore old_protocol, shouldn't we get it from pandas if possible? e.g. this will break if their source code changes."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "This should consume less resources because str_replace don't need to assign arrays with all the values"
    },
    {
      "prediction": "This is a hack.",
      "reference": "It would be better to pass `param` as the second argument here, so that the parameter declaration is printed alongside the type. Same thing for the changes in `ffi.c` and `lambda.c`."
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "Do we need to set the members to final like submitTime, submitUser ...? They are only used by getter method."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "That makes this error message incorrect; if someone has extended Cms\\Classes\\MediaLibraryItem, then this error message will read \"Class My\\Classes\\CustomMediaLibraryItem has been deprecated\"."
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case.",
      "reference": "Is it worth injecting the whole configuration object for just one setting? Would it be more generic to pass an $options array with the override_from in it? I'm not completely opposed to passing $config, but since we've avoided it so far, it seems like it would be cleaner to maintain that separation. Simply adding a getOptions method to the factory would make this a lot more readable."
    },
    {
      "prediction": "How to do this?",
      "reference": "Just curious: where do these pin numbers come from? I see you took the SPI0 pin numbers from the Arduino board layout which is good, but I can't find such a relation for `SPI1`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the method.",
      "reference": "Isn't that already too late? I'd expect, that the LinkageError occurs the first time, we have the class instance (the classloader tried to load the class) - or do we get a partially linked class back, and we get the exception when retrieving the methods?"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "nit:s/Traceparent/traceparent/ - As per the spec header name is all lowercase."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We need to have unit tests for it since it is now a public function. Also I'm not a fan for making this movement since `relPath` doesn't consume any info in this pkg."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We generally avoid wildcard imports. If you feel like changing it back, great. Otherwise, no big deal."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "We also have a typo on the line above! OUt or Out?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "OH! These are text.... (Ignore above)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How was this set before? Was it just ignored?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `stripe_token` parameter?",
      "reference": "Should we `save!` here?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "sizeof(port) seems ever-so-slightly clearer."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Not sure if this has been discussed. I wonder why SourceGroups and DestinationGroups are not in From and To NetworkPolicyPeer as NetworkPolicyPeer already describes the source/destination of the traffic."
    },
    {
      "prediction": "I don't think this is the case, but it would be better to do this with the `--mode=normal` option.",
      "reference": "This doesn't account for `:bind --mode caret ...` (i.e. `--mode caret` instead of `--mode=caret`; both work). Do you see an easy way to make that work?"
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "Is this map used for durable state anywhere? If so we probably want to keep ConditionFailedError as 2"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You can use `http.MethodHead` here."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "And another empty test. Please remove until there's content."
    },
    {
      "prediction": "I think this should be a `Promise` or `Promise.resolve` instead of `Promise.resolve`?",
      "reference": "You really didn't need to do any of these, we need to remove the API client from source eventually anyway."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "seems pretty strange here because TiSession contains PDClient."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "I created a test method for this scenario. Would you normally split it out like that or bundle this into one of the existing test methods? I'm more accustomed to creating lots of separate `it` blocks in nested `context` blocks in rspec"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "should it be `newsessionqueue` or `newsessionqueuer`? In case we'd like to be consistent"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Maybe add `@lucene.experimental`? We are exposing (slightly) internal details about `IndexWriter` so maybe we need to reserve the right to change this API in the future ..."
    },
    {
      "prediction": "I don't think this is a problem with the `puppetdb_status` command.",
      "reference": "@johnduarte I know this isn't part of your code change, but it seems to me that this `curl_with_retries` is not necessary. If the `retry_on` host command is successful, isn't puppetdb ostensibly listening to the ssl port as well? What do you think about removing that `curl_with_retries` after the `retry_on`?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `selector.Selector` and `parser.Labels` functions.",
      "reference": "Does an empty struct really take less storage than a bool? I guess it must be, or else you wouldn't have changed this, but I'm curious about the detail."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: This should perhaps be called `waitForAndReportSelectionChange`, as it affects braille as well, not just speech."
    },
    {
      "prediction": "I don't think this is a problem with the error message.",
      "reference": "nit: I suggest that we rename `tag_error_response` to `tag_resource_success`, as later in line 132 we're returning an error if this value is *not* truthy."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I am missing return typehint"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "_base_ = 'retinanet_pvt-t_fpn_1x_coco.py'"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should remove `throws Exception` here, since we're catching it anyway and triggering `onAuthFlowError`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "a super thin wrapper like this makes me think we should consider not having it, instead just defining in the plumbing.api the publisher and subscriber interfaces we expect a ps dependency passed in to support and then to pass calls directly to that thing rather than through this wrapper"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Waiting for the pull takes a long time. This message informs the user that at least one of the images being pulled is available. Please leave."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We should set a 1.7 upper bound for this as well. :smiley:"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Lodash mixed in with WordPress dependencies"
    },
    {
      "prediction": "I don't think this is a problem with the `StripeEvents.find_by_stripe_id` method.",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "perhaps we should test that users cannot edit the profiles of others?"
    },
    {
      "prediction": "I think this is a bug in tservers.ServerTestBase, but it's a bug in tservers.ServerTestBase.",
      "reference": "Does this mean the content changed with the new pyopenssl version? Is Wireshark already compatible with this new format?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "line is 147 characters (from `lll`)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Perhaps move this option into a separate speechViewer section, as we are planning to also save position information as well."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "This is not a segment responsibility this query should be in exporter-File module"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `--export-fixes` option?",
      "reference": "Did you measure the performance with and without this option. Do we want to export fixits even if the `clang-apply-replacements` tool is not available in the user's PATH?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "What if we do not change this file ? Are we using this `pkg/disk/v1alpha1` elsewhere for block device requirement?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "regarding dropping the port/host/uri methods on Nod: this would `options[:port] = target.port if target.port`"
    },
    {
      "prediction": "I think this should be a static method?",
      "reference": "good question - I vote we just remove, up to you if you want to handle in this PR though. (as it would require changing the places you call it; maybe moving the test? Though my guess is if we don't now, we never will."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `data.cache?(:bundler)` and `data.cache?(:bundler)`",
      "reference": "This is so that if we turn on bundler caching globally it still won't affect python etc. Same inheritance logic as for the cache slug."
    },
    {
      "prediction": "I'm not sure if this.SupportsAllocation(contexts) is true?",
      "reference": "[You can ignore it] Maybe a better method name would be IsSupported or HasSupportForAllocation?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Why is this changed to `\\*`? The behavior of the code on line 42, shows that `*` is what's handled?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "I think this should either return `-1` or throw. I think my vote is on the former."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I am confused, I've read 2, 3 and 5 seconds in various places"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `Content-Length` parameter.",
      "reference": "Any particular reason you chose int64 instead of int? This requires adding type conversions throughout the code below."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "this string should really be a local constant. it's repeated below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Number types are hard  . Should we be considering byte/sbyte? What about unsigned variants that would otherwise fit in a signed 64 bit integer like UInt16, UInt32?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "`Assert.True(true)`...   xunit used to have Assert.DoesNotThrow  "
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `s3_credentials` variable.",
      "reference": "should this be an env var like the other `S3_*` values?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `parentNode` and `parentNode.removeChild(node)`?",
      "reference": "If you do go this route, I think it would be worth adding a note here that IE 11 is the only reason why we're not using the more obvious `node.remove()`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `keys()` method.",
      "reference": "The added text doesn't really match why it's possible. Maybe it would be better to name that as a separate case for this checker? (e.g. dict lookup is quicker than list comparison)"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "just whether we are not missing some doctrine extension because above this attribute is nullable position and it shows int instead of int|null but maybe for lvl2 it is OK"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Prefer `Stream.anyMatch` instead of iterating over all slots."
    },
    {
      "prediction": "I think this is a bug in VkImageDrmFormatModifierListCreateInfoEXT, but I think it's a bug in VkImageDrmFormatModifierExplictCreateInfoEXT.",
      "reference": ":grimacing: yikes, thanks for catching this!"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "`Binded` is weird. I think it needs to be something with `Bound` in it (and drop the `Mvx` bit) like `ViewHolderBound` or something."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can we have String() and GoString() implementation of `apis.CStorPool` struct to pretty print it."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Like I said, please replace by `EXPECT(kTokenString)`"
    },
    {
      "prediction": "I don't think this is a problem. I don't think this is a problem.",
      "reference": "Will you please update the copyright message to `2021` for classes that you modify?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is there a better way to filter these other than relying on the hashKey. I few like this might now be trustworthy in the long run. If angular ever removes this property, this feature would be broken."
    },
    {
      "prediction": "This is a hack.",
      "reference": "No need to check dynamo_exited"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "from linter: >method SetTlsCACertificate should be SetTLSCACertificate"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "this data had incorrectly aligned timestamps (which wasn't the point of the test)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since this is workflow agnostic, should we put this in common?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "using the `@abstractmethod` decorator wouldn't be better?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was crashing the app during EDIT on boolean Doctrine Embedded properties"
    },
    {
      "prediction": "I don't think it's a bit of a hack, but I'm not sure if this is the case.",
      "reference": "Will this be backwards compatible with the previous path?"
    },
    {
      "prediction": "I don't know how to use the <see cref=\"IScope\"/> for this implementation.",
      "reference": "what is potential use for current scope? It seems you'd only want it to stop it. But if you get current scope you never know if it's yours to stop - i.e. this is not safe or correct to stop current scope. So I wonder should we even try to expose it?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `googlesitekit-user-input__buttons--next`",
      "reference": "I think this is likely the only additional change needed on the original PR."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Please revert changes to unrelated file"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can test use a Mockito mock instance instead?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Bit of a shame about these multi-line strings in annotation parameters - they're not a deal breaker but just make the diff noisier"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "we can remove this one as this is not used any more"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "we don't really need an extra error flag"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "any chance you could just fix the processors plugin?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "We may keep this config unchanged since `use_depthwise=True` by default."
    },
    {
      "prediction": "I'm not sure if this is a thread-related function.",
      "reference": "Maybe add i#956 in this log as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "if (StoreInbox* storeInbox = getStoreInbox()) {"
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "what is this, is it going to be used later?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "@anodelman test failure is probably due to this, needs to be fixed to `(\"Host #{host.name}\")`"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "I'm not sure that we need this anymore, but that can be a separate discussion."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "The formatting seems different from the rest of the code"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we have a unit test for this?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: put params in new line"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `unifiedDashboardEnabled` option.",
      "reference": "The button for the date range selector has incorrect width since it has `padding-right: 8px` which sets the width to: `44px`. Can you review to make the button `36px` on small screens as per the AC?"
    },
    {
      "prediction": "I don't think this is the case where we need to check if the code is in use.",
      "reference": "This should be inside the set routine IMHO: matches the others; all callers need it; simplifies code here."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "MAX_RETRY_TIMES makes much more sense."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`saveSession` allows easier mocking - just save function which You need, instead full interface"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "No docs for the new param here?"
    },
    {
      "prediction": "I don't know if this file is used in compliance with the License, Version 2.0 (the \"License\"); you may not use this file except in compliance with the License, Version 2.0 (the \"License\"); you may not use this file except in compliance with the License.",
      "reference": "This file is unrelated to the aims of this PR. Please remove. If it is needed to demonstrate Sonar Deltas then it has been proven and can be removed."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "minor: `Export all ended spans to the configured Exporter that have not yet been exported.` - This is the spec description. Lets use something on that line. \"queue\" is not necessarily present for all processor."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "is this deliberate? or testing?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I want to get more perspectives regarding this one. Making it `readonly` makes me feel that we're assuming the head should never change, and my worry is that other code might assume it (e.g. they might cache the value and assume it will never change). While this is true for now, I guess in the future we might want to support something like `PrependProcessor(processor)` or `InsertProcessor(index, processor)`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This isn't critical for test coverage, but it seemed off that we had disabled wrapping the reader."
    },
    {
      "prediction": "I don't think this is the case for the `EState_VSA` and `EState_Lipinski`, but I don't think it's the case for the `EState_Lipinski` and `EState_Lipinski`, but I don't think it's the case for the `EState_VSA` and `EState_Lipinski`, but it's the case for the `EState_Lip",
      "reference": "Please remove Descriptors3D from this file. We just did this in master."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "You could pass the MetaClient instance in ctor, and create a new instance if nullptr."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What does this do? Seems like a poor mans mutex/semaphore?"
    },
    {
      "prediction": "I'm not sure why this is called before Write().",
      "reference": "This is a breaking change, and cannot be made. We have committed to this API for v1."
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "Can also drop corresponding types from docblock here"
    },
    {
      "prediction": "I'm not sure if this is a new session request?",
      "reference": "This change is unhelpful to users."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "why is this variable introduced? Please stick `_o.Test3.A` directly in the call below."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `verifyToken` parameter.",
      "reference": "do you mind sharing what is the reason for this change?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `list_proposals_limit` parameter.",
      "reference": "thoughts on putting `alter_query { |rel| rel.limit(@closed_proposal_limit) }` in a method that we can call here? That way we can have a test for this logic without needing a controller spec."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "Perhaps `@node` throughout"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Shouldn't this default be 'normal' ?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: type this"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "These command names are specific to Chromium-based browsers. Please move to `ChromiumDriverCommand`"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "lets print nodeName that got passed also"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should be `if sys.version_info[0] > 2:`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Is there any need to pass this through `string_metric_parse`? I believe you can either create an off_t or just pass 0, with no need to added a string conversion into the mix."
    },
    {
      "prediction": "I don't think this is the right thing to do with the print_option_arg.",
      "reference": "Let's not use a form of hungarian notation in naming our variables"
    },
    {
      "prediction": "H2O_PROBE_CONN(RECEIVE_REQUEST_HEADERS, &conn->super, conn->_req_index, &conn->req.input.method, &conn->req.input.authority, &conn->req.input.path, &conn->req.version, &conn->req.headers.entries, &conn->req.headers.size);",
      "reference": "Seems like we are calling the probe twice?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `exec` command.",
      "reference": "I think we'll want @rickmanelius (or somebody) to go through all the help and make it more accessible. Probably later in the cycle. But \"Run a command in an app container\" doesn't do it for me :)"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Have not tested this yet, lets see if tests complain, but I suspect it should be as easy as this  "
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "no big deal but we don't we just use a list to keep the order? I don't think it's likely to have a duplicated columns if that was the concern."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "See above, same for all similar cases below."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "where is this coming from?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "We can also drop `plans.includes_screencasts`, right?"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "wouldn't `int.to_bytes(counter, 32, 'little')` be equivalent, clearer and faster?"
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "I don't see why this is in porcelain since it's just a free function, with no dependency on plumbing or the `a` receiver. I think it should be moved to `protocol/storage`. It's exposed unnecessarily widely here."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Could we only do this for all time? Because that's what is causing problems rn?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This looks better than before, but we'll now likely run into issues with `'` characters in the spec. Maybe we can just use `manager.call_strings` instead?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should this replace `splitSize` instead of adding a parallel call? The `SparkReadConf` is not yet released, so we can change it still."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "To reduce complexity, please use OSError on Python3 as well."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `follow_selected` command.",
      "reference": "That seems wrong."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Yes, this is needed here. This is a builtin user who just reset their password."
    },
    {
      "prediction": "This is a hack.",
      "reference": "This seems to move the storage of temporary files to the CWD. Is that right? I don't think we should do that. If the process gets interrupted, we should try our best to clean up, but if even that fails, it'd be nice if the mess was left in a different directory. Maybe we should have a directory explicitly for builds?"
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "Please explain why a user would enable this (space savings), and the requirements for this option to be safe."
    },
    {
      "prediction": "I think this should be a `useSelect` function, but it's not a `useSelect` function, but it's not a `useSelect` function, but it's not a `useSelect` function, but it's not a `useSelect` function, but it's not a `useSelect` function.",
      "reference": "I think the `undefined` checks still need to be removed from here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is there any particular reason to have 6?  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The biggest chunk does not guarantee that it contains the biggest CIDR-aligned range. If we don't care too much about a few CPU cycles being wasted, then I'd suggest to merge the if-statements."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "instead of doing the if err := __; err != nil { return err } thing, you can do errs = addErrs(errs, ___). If you want."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "nit: Is this error message accurate?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `src_is_bare_or_bare_user` flag.",
      "reference": "Ouch! :man_facepalming: And of course, this worked for me because that evaluated to false when I was testing the bare-user path."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Parentheses aren't needed here. `if len(statusParts) > 0 {` will suffice."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's a string, but it's not a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string, so it's a string.",
      "reference": "// the test is skipped on given servers because it will fail."
    },
    {
      "prediction": "I'm not sure why this should be called.",
      "reference": "The name of the test should be updated to \"it 'should return bad_request if api key is invalid\""
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Use `==` in this case instead of `is`."
    },
    {
      "prediction": "I don't think it's a CStorPoolPhase, but it's not a CStorPoolPhase, but it's a CStorPoolPhase.",
      "reference": "Please put it like this: `CStorPoolPhase is a typed string for phase field of CStorPool`"
    },
    {
      "prediction": "I think this should be a good idea?",
      "reference": "variable must be in camelCase => $newStock"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "unnecessary conversion (from `unconvert`)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "... is probably automatically vectorized, since it has the same speed as `System.arraycopy`"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Is there anyway to get rid of the global variable, if it is specific for each task, can you add it to the `mtask` struct?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Surprised to see this old syntax here, but not _that_ surprised."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "It is good to mark it! Maybe we can remove the method for Vavr 1.0.0 - but for now it can stay as-is. Thx!"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `glog` or `glog`?",
      "reference": "exported func New returns unexported type *pool.pool, which can be annoying to use"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Sorry, I feel like I'm missing something - where does this get called?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@guihecheng Thanks for the fixing! Actually this is not the dup codes, when we first registerNode, then update the nodestatus immediately, or the node will keep not ready for 10s. And do you have other ways to refactor it?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "How portable is this? (e.g., Windows). I'm relaunching tests of windows because they failed for other reasons."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What this does is narrow down what we are saying the descriptor set is requiring. This is a good thing, but doesn't go far enough, we are still potentially setting unused bindings to either a required state or an invalid one. set_binding_pair.second is a map of the binding/requirements from the bound shaders... and instead of marking all bindings, looking at that will mark only the used ones. Will open a new PR"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should use `codes.InvalidArgument`, same as above line 1033 and 1036"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please revert this file."
    },
    {
      "prediction": "I think this is the default URL opener.",
      "reference": "Probably in another PR, I think the package should be renamed to `servicebus` to be consistent."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "curious: are we planning to add link to each of the rules in the message?"
    },
    {
      "prediction": "I don't think this is a good thing to do with the `SettleDepositRequest` and `SettleDepositResponse` and `SettleDepositResponse` methods.",
      "reference": "line is 123 characters"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "same here; `@param array $user Array of user data`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "A quick read of this test indicates that we're changing the behavior of this api, and so the test needs updating. Is that right?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `RecyclerView` and `RecyclerView.RecyclerView` and `RecyclerView.RecyclerView` and `RecyclerView.RecyclerView`",
      "reference": "Register needs lowercasing"
    },
    {
      "prediction": "I don't think this should be the default value for the proxy user?",
      "reference": "This should belong to FlowContainer class."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I think there is a chance that on disable/enable cycling, referring to `self.window` is problematic. In the `__init__` method `self.window` is set to None. If `__init__` gets called before `_run` exits the `while` loop then we wont call `self.window.destroy()`. Can you use non-instance variables after this point? I don't think `self.timer` is used outside this function, if so, then I'd prefer it also be a local variable."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I was confused by this env name variable, assuming it was the value, not the name. Silly nit, but maybe name it noninteractiveEnv?"
    },
    {
      "prediction": "I think this is the default value for the default value, but it's not the default value for the default value for the default value for the default value, but it's the default value for the default value for the default value for the default value for the default value.",
      "reference": "  nice, having the \"overwrite\" default makes this change backwards compatible, right?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "It doesn't make sense to accept all 2xx status code. For example, `203 Non-Authoritative Information` or `205 Reset Content`, etc."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Found a better choice here that doesn't involve object creation: StringHelper.startsWith()"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't we consider the situation where it doesn't find a plugin?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Do not understand why this needed for table. All new classes defined in the `preview` namespace."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Kept the same property value even though it is now in Common to avoid breaking existing clients."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "TODO: this is temporary until we figure out case sensitivity for metrics evaluators."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can we just kill this TODO?"
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "This appears to be a change in error handling due to a dag upgrade."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "These changes look like a hosts file _must_ be provided?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@akohlmey Just make it a cast like the others. I dislike it either way, but that's the price we pay for Python 2 support."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I wonder if the default here should be nightly? I won't block on that though just a question for a follow up."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Also not for merge to master."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit `non-standard` might be a bit subjective - maybe \"Cron schedule {blah} is in an unrecognized format. Dagster cron strings must consist of five characters separated by a single space chacater\"."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "ARM emulator gets tripped up on the copy/paste menu when tapping the text. Tapping on the text field isn't necessary for setting text."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "extra word lookup removed"
    },
    {
      "prediction": "I don't think the promise is resolved.",
      "reference": "Will you link to {!webdriver.promise.Promise} here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@AdrianLxM finally found some your bug too :)"
    },
    {
      "prediction": "I don't think this is a hack. I'm not sure if this is the case.",
      "reference": "This crashed in an app using descriptor_indexing with some unbound descriptors."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I think we might want to keep these marks separate? Then we can create a new `workflow` file with 3 jobs: 1) Prime stdlib 2) Prime batch 1 of external 2) Prime batch 2 of external"
    },
    {
      "prediction": "I'm not sure if this is a child view model cache?",
      "reference": "Throw `fragInfo.CachedFragment.ViewModel.GetType()` into a variable so it's not evaluated each time."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Rather than just getting rid of the memoization maybe we should use an `after_save` filter to set it to `nil` so that it will be recomputed on next read?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "JS abstraction leaks so this should be `if (el.parentNode !== null) { el.parentNode.removeChild(el) }` @developit  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: change it to `Exchange: unexpected status 0x%x` so that we'll know where this issue came from as well as making it easier to decode."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Name of constant is not appropriate. Name of constant should make use of version no. as suffix. The constant can be a typed string versus a string."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `--interactive` or `--tty`?",
      "reference": "@glennsarti you want to validate this on Windows? IIRC this won't work"
    },
    {
      "prediction": "I think this is a hack, but I think it's not a good idea to use `strictTraceId` or `namesLookback`?",
      "reference": "ps I'm ok to add this as a elasticsearch property instead. ex zipkin.storage.elasticsearch.names-lookback (we have similar things in cassandra)"
    },
    {
      "prediction": "I don't think this should be a function. I don't think this should be a function.",
      "reference": "Curly brackets here `{ (breakLine) xx (breakLine)}`"
    },
    {
      "prediction": "I'm not sure if this is the right one?",
      "reference": "Can you check this case Assuming you have a dashboard with 2 users, test1 and test2 Currently logged in user is test1. You should not be able to change it to test2. You open dev console and paste in `countlyGlobal[\"member\"].username = \"test2\";` then you enter value test2 in the input and it is allowed and form would be submitted. Would server side validation deal with such case?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "since we're changing this class, let's fix the default class name as well. it should be com.mysql.cj.jdbc.Driver"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `ensure_system_roles_exist` method.",
      "reference": "At load time, we ensure the config'd objects exist."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Is there a test for this case?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "This copy doesn't match what I had in my mockup. I think it's better to call them episodes."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "For some reason it worked for frontend even before this change."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the lock guard?",
      "reference": "Can we encapsulate this in a function so if we want to change it against we don't have to change all call sites?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Maybe a good opportunity to do a related improvement: The parameter `total_blocks` in `bootstrap_attempt::process_block` shadows a field with the same name, so maybe rename the parameter to `total_blocks_a` The parameter and field are incremented at the same time, but the field is used by `populate_connections` as well, so I assume they mean different things. Other than that, LGTM"
    },
    {
      "prediction": "I don't think this is the default value for the default replica factor.",
      "reference": "Please revise the naming of these two flags. _**default**_ is the value we take when user doesn't provide. You could infer from the fact how `default_parts_num` are used."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't think we should have separate \"transformer\" and \"generator\" terms. I would suggest renaming this existing class `ImportTypeTransformer` to `StandardImportTypeTransformer` and renaming the interface `ImportGenerator` to `ImportTypeTransformer`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I believe `tag-matchers` is the proper form for this filename. Only components should use pascal case, I believe everything else should continue to use kabob-case."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "same here, move this one down"
    },
    {
      "prediction": "I'm not sure why this is the right place to create a new order.",
      "reference": "Some could be created as superadmin instead, to add more special cases. Also, the reason behind this change should be described in the commit msg and the PR description."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "Is this required?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "`--public-volume-create-allowed=true` and set the default to `true`, then use `!c.Bool('...')`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Could we use `0x7ffffffe` instead, since `INT32_MAX` is an ID of a _pull_ stream? Other than that the PR seems ready for merge. Thank you for working on the fix."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Might as well add a docstring for the new `exit_code` parameter too."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "`poll` and `remove` have different meanings."
    },
    {
      "prediction": "I think this is the default value for the default value for the default value for the default value for the default value for the default value for the default value.",
      "reference": "What's the perf impact of writing bloom filer? Does it make sense to enable it by default if the perf impact is minor? Would be nice to include benchmarks?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Remove `HIP_UNSUPPORTED` - it is an alias"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "i think we should return an empty list instead of null here."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Is it really necessary to store them in a new setting? I think it should be enough to store the credentials in `ProxyConfig.direct()`. Then AntennaPod does not need to store multiple different proxy settings. Also, it will not change existing users' settings (currently the proxy settings would be lost on upgrade)."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This is a mess. Can it be broken out as a separate function using ifs and return statements, which would also make it more debuggable."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This stuff is a bit ugly and should probably become a utility. The main problem is that ``.map`` is being abused a bit."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Maybe there is a better way here so that we don't even bother triggering a storage query since we want an empty list here."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "just curious, `region` is not used in the AWS IAM client, afaik. But I see this is a general field for clutch clients, is it just ignored internally?"
    },
    {
      "prediction": "This file is part of the code, but I don't know if the License is available.",
      "reference": "Why are we doing that change?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why && changed to || ?"
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `repartition(npartitions=1)` instead of `repartition(npartitions=1)` and `repartition(npartitions=1)` instead of `repartition(npartitions=1)` and `repartition(npartitions=1)` instead of `repartition(npartitions=1)` and `repartition(npartitions=1)` instead of `repartition(npartitions=1)`",
      "reference": "can you please change this to `_collection_to_single_partition()`, like we've done for alll other helper methods defined in this module?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, I'm not sure if this is the right thing to do.",
      "reference": "This class is never used, don't import it."
    },
    {
      "prediction": "I think this is a bug in the test suite.",
      "reference": "Missing a `return`. Either way, I think it's better to add a `#if DEBUG throw;` in the catch block instead (so we keep the log in debug mode)"
    },
    {
      "prediction": "I don't know why this is the right thing to do.",
      "reference": "Files should have an extra line at the end of them."
    },
    {
      "prediction": "I don't think this is a thread-safe implementation.",
      "reference": "I think we could replace this (well the backing field) with `BlockingCollection` when we drop NET35?"
    },
    {
      "prediction": "I don't think we should drop the columns?",
      "reference": "Can you show before/after output in the PR description? From a cursory look, seems like it will just drop the duplicated column which isn't consistent with pandas' results."
    },
    {
      "prediction": "I don't think this is a bug in Bolt.",
      "reference": "Added validation that `config: transports` isn't used @adreyer @katelopresti Curious what you think about having Bolt link directly to the docs site."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "This probably isn't needed anymore now?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `props` and `rest` arguments.",
      "reference": "Would it be easier to kick this import to the top of the file? It'll get stripped out anyway."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "are you sure that the privacyGroup cannot be null?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Wrapped with list"
    },
    {
      "prediction": "I'm not sure why this is the case for a non-zero base?",
      "reference": "Please move this to `pkg/stats/v1alpha1`"
    },
    {
      "prediction": "I'm not sure why this is a problem?",
      "reference": "a small nit pick ...this can go into `lib/patterns.rb` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The above TODO is no longer necessary I believe  "
    },
    {
      "prediction": "I think this is a bug in zfs.",
      "reference": "Why is this change required ?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This really is an excerpt. ;-)"
    },
    {
      "prediction": "I don't think this is the case for the `isWithinFunc` function.",
      "reference": "@acud The reason why the default is now `true` is because the chunk must be in the neighborhood of the storer peer with this change. The majority of the tests expect a valid receipt so the closest peers in the tests must be in the neighborhood. As of writing this, there is only one test that expects a peer to be out of depth."
    },
    {
      "prediction": "I don't think this is needed, but it's not needed to load postgresql plugin",
      "reference": "This is what breaks the build. Apparently w/o this line, `sqlite` package is not even compiled. With this line it gets compiled but compilation fails because we don't use CGO for our production Linux builds and > ***Important: because this is a `CGO` enabled package you are required to set the environment variable `CGO_ENABLED=1` and have a `gcc` compile present within your path.***"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should be all slots"
    },
    {
      "prediction": "I'm not sure if this is a static method, but it's not a static method.",
      "reference": "Need to add deprecated annotation and call the new fixed method to avoid the API broken issue."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was just fixed in mozilla-mobile/android-components#4892. @pocmo is cutting a new Android Components 19 dot release today, so you'll be able to jump to the new version and restore the build type."
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "Leaving this log line because it helped me to diagnose that the reconciler client was using a different cache than the event sources, so not always seeing the injectable that triggered the reconcile."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Do we need also to protect access to `mset.js` and `mset.jsa` or even `mset.store` down below? (not sure if those are immutable or not)."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I'd rather you do this under `if info.filledInMerkle {` since that's the only place it's relevant."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "*NULL_DEREFERENCE:* object `leaderUrl` last assigned on line 348 could be null and is dereferenced at line 351."
    },
    {
      "prediction": "I don't know why this is the right thing to do with `orcid`?",
      "reference": "Since the IdentifierScheme's don't change without us making additional code changes, perhaps this should be added as a constant as we previously did with Perms?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "nit: We can revert this now."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Oh, that's the reason why you have two different data structures here. Does the order of the `selectedItems` list matter? If not, I think it would be more clear if both would be a Set."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Should be named getDescription, since the other description functions are named that."
    },
    {
      "prediction": "I don't think this is the case where we need to set the EyeBufferSize to 1920, but I don't know how to set the EyeBufferSize to 1920.",
      "reference": "Don't we want to do this for g2 4k also?"
    },
    {
      "prediction": "I don't think it's a `Buffer` object, but it's a `string-to-arraybuffer` object, but it's a `string-to-arraybuffer` object, but it's a `string-to-arraybuffer` object, but it's a `string-to-arraybuffer` object, but it's a `string-to-arraybuffer` object, but it's a `string-to-arraybuffer` object.",
      "reference": "I would prefer if we don't add this package as it's unsupported, and I expect not necessary. Node buffer supports many formats - is it not possible to use one of its helper functions to load the content?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I don't think this is used any more, please remove."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "actually use type_name=print_config_type_to_string(self, with_lines=False) to populate this"
    },
    {
      "prediction": "I don't know why this is the right thing to do with the `delete_local_resource` option.",
      "reference": "We should be using dependency injection here, instead of fetching the config factory at the last minute from the container. That would allow us to more easily overwrite the \"delete_local_resource\" setting in tests."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "everywhere else in the project, `LOGGER` is used"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why is this value set to \"min_by\", and what are the implications of it? Does `&:to_f` play nice with semver (e.g. 1.2.0)?"
    },
    {
      "prediction": "I think this is a bug in enzyme-adapter-react-16.",
      "reference": "typo --> gloabl"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Wanted to double-check: does the `log` middleware still set its own \"empty\" value (should default to `-` at least for the default log format)?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "It would be better to just change RWD to throw IllegalStateException if you attempt to execute a command after quit (unless it's a second call to quit())"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Is this going to be configurable? If not, it should just be removed for now."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Maybe just one import line - `from collections import OrderedDict, Mapping` ?"
    },
    {
      "prediction": "I think this should be a list of integers. I think this is a list of integers. I think this should be a list of integers. I think this should be a list of integers. I think this should be a list of integers. I think this should be a list of integers. I think this should be a list of integers. I think this should be a list of integers. I think this should be a list of integers. I think this should be a list of integers.",
      "reference": "Btw this class probably doesn't belong in PMD. It says it's there to test UIs, but arguably UIs can use their own test fixtures, and this in in src/test so probably not even shipped anywhere."
    },
    {
      "prediction": "I don't think this should be done here.",
      "reference": "Maybe we can group each `finishResolution` call with the corresponding `receiveGet...` call? That would make the connection more clear when reading the code."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `server_conn` method.",
      "reference": "Can we take this out of the constructor here and just use the config value? (This would also make the other proxy mode cases obsolete)"
    },
    {
      "prediction": "I'm not sure if this is a required field? I'm not sure if this is a required field?",
      "reference": "Please flip the conditional to be `if (field.required) { ... }`."
    },
    {
      "prediction": "I don't think this should be the case.",
      "reference": "should we create a fixture without first name and last name and have a spec like this one that uses it to make sure nothing errors out when they are not present?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "It seems odd to require all Python snippets to have this method when it's not relevant for messages.snip or the discovery snippets. (I see that we're already doing something similar with generateModule/generateBody where some of the implementations are empty. This also seems strange to me.)"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "What about this: \"// Corresponding PMT does not exist.\""
    },
    {
      "prediction": "I don't think this is the right thing to do with the `config_file`?",
      "reference": "You don't need af ormat specified here."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Nitpick: import ordering"
    },
    {
      "prediction": "I don't think this should be a function, but I don't think it's a function.",
      "reference": "code smell here, a function that create a reward calculator from transaction processor?"
    },
    {
      "prediction": "I'm not sure if this is a runtime var manager.",
      "reference": "I don't think the `A` is idomatic is it?"
    },
    {
      "prediction": "I'm not sure if this is the default action.",
      "reference": "nit: the others use the method name in the api and not the class name of the api"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does it work to run all the sil diagnostic passes before we serialize? That would be more consistent with what the normal compiler does in `FrontendTool.cpp : performCompileStepsPostSILGen()`"
    },
    {
      "prediction": "I don't think it's a teacher?",
      "reference": "You left in a puts."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Hmm, should we also cache the `smoothingScore` for this hit? Or, if we will keep it at returning `0`, couldn't we remove this impl and inherit the default from `Scorable`?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `npm-publish` option.",
      "reference": "I removed that from here because I am hoping that will stop the random unwanted updates to the website with unstable versions."
    },
    {
      "prediction": "I don't think this is the case for Linux 3.14 and later.",
      "reference": "Nit: missing period."
    },
    {
      "prediction": "I think this is a bug in S3.",
      "reference": "how **to** deny Simple Storage **Service**"
    },
    {
      "prediction": "I'm not sure why this is a good idea, but I'm not sure why this is a good idea.",
      "reference": "Were you having trouble with timeouts in general acceptance tests or only the editor test? It's possible to set timeouts on a per-test basis by using `this.timeout(25000)` within the `it()` function. I'd like to drop the global timeout in the future if possible rather than increase it - in some circumstances a failing test can have a knock-on effect which makes all later tests timeout so Travis can get hung up for a long time if no one notices and cancels the build."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't think this is necessary."
    },
    {
      "prediction": "I think this is a bug in the API.",
      "reference": "Instead of blindly ignoring all errors, this should just ignore the volume not found error."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "The `rowPosition` will be ignored if the position column is not projected."
    },
    {
      "prediction": "I think this is a bug in zfs.",
      "reference": "Is there a possibility of a clash between periodSeconds and timeoutSeconds? For instance, the current probe is not yet timed-out and the next one has started."
    },
    {
      "prediction": "I don't think this is the default factory, but I don't think this is the default factory.",
      "reference": "This logic is already been performed in `CommandLine.defaultFactory().create(cls)` ... whats the point of repeating it here?"
    },
    {
      "prediction": "I think this should be the same as `countCols`, but it's not the same as `countSourceCols`.",
      "reference": "Please change from `let` to `const` here and above. Setting value to `this.hot.countSourceCols()` should be enought probably."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "Somewhat nitpick: I see the `!=` pattern mentioned in the fluent-bit style guide, but imo, it would be safer to check that a fd is non-negative with ` > -1` or `>= 0`"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Use the new Ruby 1.9 hash syntax."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `gogs/modules/bindata` or `gogs/modules/log` or `gogs/modules/user`?",
      "reference": "Please host to a GitHub repo."
    },
    {
      "prediction": "I don't think why this is the case.",
      "reference": "The Error log message should not expose internals. The message should be something like this `\"done split failed for address %v\", tagr.Address`. Also, the Debugf would be more informative with the address in the message."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `loglevel` option.",
      "reference": "can we rename `fileLogLevelUsage` to be more generic like `instanceLogLevelUsage`? Same goes for other var below like fileLogLevelFlagName, FileLogLevel."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Does this one not need the `tabContent` object used in the other files?"
    },
    {
      "prediction": "I don't think this is the case where the ELB is unmanaged.",
      "reference": "Our use of the terms `managed` and `unmanaged` in CAPA is interesting. I think we should probably update the docs (as part of a separate PR) to explain that we are referring to whether its CAPA managed infra. As opposed to meaning AWS managed service."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Looks like all of these can be put into a list."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: \"*mapping\" for a map is unnecessary. Consider calling this `originalNames` or similar."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please split this into two sentences; i.e. \"This profile will be permanently deleted. This action cannot be undone.\""
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "NPE here and in other APS plugins"
    },
    {
      "prediction": "I don't think this is the case for dynamic controller modules.",
      "reference": "Thanks for the fixing, and could you please provide more details for this bug? Because we have the deduplication mechanism in cloudhub, so it will has no problem."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "These could be final"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "highway have the same problem we can add a new method in invocation: mergeContext 1.if new context have more items, then addAll to new context, and replace old context 2.if new context have less items, then allAll to old context directly."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Created a single error so it's not interleaved in log"
    },
    {
      "prediction": "I don't think it's a bug in IE9, but I think it's a bug in IE9.",
      "reference": "`isIE9` was reverted. Shouldn't this condition be reverted as well?"
    },
    {
      "prediction": "I think this is a bug in LuaScriptInterface::callFunction.",
      "reference": "Sorry if I'm being too pedantic here, but wouldn't it be nice to have standard parameter name? Like using `defaultValue` everywhere."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's a string, but it's not a string, but it's not a string, but it's not a string.",
      "reference": "Remind me again: what's the point of having new clients connect to both -0 and -1? If we ever have to blackhole -0, we'd have to blackhole -1 at the same time, right? What is supposed to be the difference between the two? Is it just that someday we might want to have two ELBs, and this will help load balance between them?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why not go back to `c.setPingTimer()` here instead so you don't need the new boolean in setFirstPingTimer()."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We should figure out why so many of these files have an invisible change on the first line: Are we writing out some sort of byte order mark?"
    },
    {
      "prediction": "The \"License\" is not included in this file.",
      "reference": "Was this our code @csrwng"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think you need `.untaint` here."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `bolt-project.yaml` file.",
      "reference": "Why are we including the `files/` directory in this check? I know `tasks/` and `plans/` make sense, since you can reference content in those directories from the CLI, but I don't think you can for `files/` (unless I'm missing a command)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "And again. The reason it's bad is that if someone uses a JDK not produced by Oracle they won't have this class."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can we rename this field to `Subject`? Looking around, it seems like 'subject' is the standard terminology for this stanza  "
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "Remove additional whitespace."
    },
    {
      "prediction": "I think this is a bug in the browser.",
      "reference": "We should add `Secure` as well"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I presume this isn't a big deal"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe {}, even though no multi-line body?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "We can try something like this: response.should render_template(:partial => 'partial_name')"
    },
    {
      "prediction": "I don't think it's a bug in the user32.MessageBoxW.",
      "reference": "Please use `isinstance(text, bytes)` instead. Otherwise, this will lead to unnecessary decoding on python 2 unicode strings."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This one is unrelated to the GetSymbolVendor removal ... the API to GetValueAsData was changed."
    },
    {
      "prediction": "I'm not sure why this should be done here.",
      "reference": "can you assert the value of this field below similar to other fields?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I'll change that to \"linkplain\" for consistency :)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This is fix. But since the history resource was relying on the bug to work, I had to do some changes regarding the history entries (eg. explicit declare that the permissions inherit from bucket)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "can't we leverage Closeable here and get some sugar&warns? Also, line 89 still calls setContext() .. is it right? or I'm missing something?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Use explicit swarm.Address when defining peerID, by using NewAddress, and remove conversion here."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "`RpmDependenciesDirectory` should start with a lowercase character so it's not exported outside of this package, it looks like its only referenced in this file."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If we make a new backbone class, we don't need to support `BasicBlock`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the BPF mode?",
      "reference": "This was an out-of-date dupe of the check on line 335"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Let's put this back"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Things like these should have been addressed before submitting a pull request."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "This one as well. Any better suggestion please?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "wonder if we should collect c.trace, c.pa.subject, etc.. while under the lock to prevent data races.. or simply move the tracing under the lock."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why is this hack needed ? Ideally, we shouldn't need that."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Minor/Nitpick: replace `1` with a constant, esp. as used in `prog/weaver/http.go` in `{{if eq .Plugin.Version 1}}`"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "nit: Looks like the whitespace got thrown off, can you fix this?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "Redo this by adding a string literal and then pressing F6 to have Resharper move it to Properties\\Resources.resx which will also create this property."
    },
    {
      "prediction": "I think this is a bug in the NATS server.",
      "reference": "Unless a log file has been specified, IMO you should set the server option to enable syslog (windows event log) here, or someplace along the service start code path. We shouldn't really rely on users to specify that when creating the service."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "It's strange here, because I saw the `TableColumn` is marked as `PublicEvolving`, but after released flink 1.12.0 it did not have any Interface compatibility guarantee. At least, it should marked as `deprecated`, and keep it a major release."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "I'm not sure regarding this approach, for me the whole text including anchors should go to resources like ` netConfigLink.setText(CoreMessages.dialog_connection_edit_wizard_conn_conf_network_link); ` You shouldn't concatenate translated values inside the code. If you need some params, please use NLS.bind()"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How often do we expect this to trigger? Should we maybe put it behind an if logger.Debug()?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How was the name `controller` arrived? Can you get a consensus for the name controller ? This may be OK for jiva. However, c-stor does not have a concept called `controller`."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "i dont think we need to explicitly single out `kernel.domainname` here since its not a TODO for OCI either right ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should we better change the operator to `<` since the variable defines the minimum size that gets compressed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm really impressed by the AppendElements addition! Very cool! :-)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "This change means that users can't easily see which version of the selenium server they're using. This is `info` level information."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This should be in qtutils and imported to here and the other place instead of declaring it twice."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Seems a bit weird to add a timeout in \"logging\" middleware, but I see that that is done elsewhere, so fine."
    },
    {
      "prediction": "I'm not sure if this is a custom form.",
      "reference": "This code is passing a non localized string when it should be passing in a localized string or it should use the name of the item being deleted."
    },
    {
      "prediction": "I'm not sure if this is a new upload, but it's not a new upload.",
      "reference": "Could we combine this with the `setState` call above, so we don't have to call it twice?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "That part that still leaves me mystified is how the String class, when populated with a value from the SQL_ASCII encoded database is set to \"UTF-8\" encoding. Since the database is SQL_ASCII, each byte in the string stored in the database is considered one character. Ruby, however, is using UTF-8, which is writing a series of one-byte code points that are only meaningful when considered in the correct encoding. When Ruby passes a string to Postgresql, the code points are essentially \"flattened\" into bytes as they are written to the DB. When Rails (through Ruby) asks for a string from the DB, where does the information about the encoding come from?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Is it a doable way and does it make sense."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "max was wrong here. As its buitlt-in, not a number, and a TypeError was thrown."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This change is not needed, please revert it."
    },
    {
      "prediction": "I think this should be the default metric.",
      "reference": "@ClimbsRocks Please add that it could be a string. `feval : callable, string or None, optional (default=None)`"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "now that I have started using, I realized, I could have named my new class singular `Sport` and not having to make this change. let me know, I will update"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure why this is changing to a hard-coded string."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is there a reason why we `str` the result? It would be nice to eventually support more datatypes here, so we want to generally aim for arbitrary JSON."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why did we update the to this api?"
    },
    {
      "prediction": "I'm not sure if this is a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string.",
      "reference": "should probably just catch `IllegalArgumentException` here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What does this error message mean?"
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string.",
      "reference": "I don't think this change is necessary. If we cast `value` to type `six.text_type`, then the next if statement should evaluate to True and do the encoding for us."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Can we move this into a method(s)?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "You could perhaps call this `strlen` (although I don't particularly care about the name as it is an implementation detail)."
    },
    {
      "prediction": "I'm not sure why this is a bug in the code, but I'm not sure if this is a bug in the code, but I'm not sure if this is a bug in the code, but I'm not sure if this is a bug in the code, but I'm not sure if this is a bug in the code, but I'm not sure if this is a bug in the code, I'm not sure if this is a bug in the code.",
      "reference": "should we have a common `Escape()` method that can be used everywhere?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The whitespace removal above here is probably unintentional :slightly_smiling_face:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we start p2p even after dispatcher? b/c dispatcher handles msg from p2p"
    },
    {
      "prediction": "I think this should be the same as the `Handle` method, but it's not the same as `Handle` method, but it's not the same as `Handle` method, but it's the same as `Handle` method, but it's the same as `Handle` method, but it's not the same as `Handle` method.",
      "reference": "Did we decide once and for all to use req/resp throughout spring?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I don't think this is a problem with the `DeleteGcsPath` method.",
      "reference": "This will delete the whole bucket, which could have unforseen consequences in normal use cases. We should be deleting args.SourceFile instead."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Lets move the whole string to next line for better readability"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the app.controller('CalendarListController', ['$scope', '$rootScope', '$window', 'Ha\n \t\t\t\t\t\t$scope', '$window', 'Ha\n \t\t\t\t\t\t$scope', '$window', 'Ha\n \t\t\t\t\t\t$scope', '$window', 'Ha\n \t\t\t\t\t\t$scope', '$window', 'Ha\n \t\t\t\t\t\t$scope', 'Ha\n \t\t\t\t\t\t$scope',",
      "reference": "Please change this back to `Error saving WebCal-calendar` (and `Error saving WebCal-calendar` only)"
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case.",
      "reference": "The vendor prefix is still being used on Chromium based browsers like Edge Chromium and Chrome. Did you mean to remove this?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Not ideal, but I used a test case orderer so I could avoid a bug that occurs when running two tracer's sequentially with different DD_LOGS_INJECTION settings."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think the condition should be ` uint(headerLengthSize) + crypto.Extension + (len(p.blobs)+1)*uint(EntrySize) > uint(maxHeaderSize)` `headerLengthSize` is only the length field. But the pack header also includes the blob type and its ID. And the result of the check, currently seems to be inverted."
    },
    {
      "prediction": "I think this is a bug in Nethermind.Mev.Test.",
      "reference": "Remove selector if only 1 version is supported"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `commandStartExternalEditing` method.",
      "reference": "Why did you remove more than the asked command?"
    },
    {
      "prediction": "I think this is a bug in the unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpacker.Unpack",
      "reference": "I just realized that we are logging time now - we shouldn't do that here, that's the logger's job. I've opened a new issue for that #444."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `GetMol(idx,sanitize=True)` method.",
      "reference": "why is the `sanitize=True` here in the docs?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `has_many :delegates` and `has_many :delegates, through: :delegations, source: :outgoing_delegates, source: :assignee_delegates, source: :assignee_delegates, source: :outgoing_delegates, source: :assignee_delegates, source: :assignee_delegates,",
      "reference": "Didn't end up using this, but I think it's useful anyway."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `Path.GetDirectoryName(filePath)` method.",
      "reference": "I'm pretty sure there's already a metadata item that contains what you're calculating here (PackageRelativePath)?"
    },
    {
      "prediction": "I'm not sure how to do this with the `project_name` and `project_id`?",
      "reference": "We want to show this button only when there is a page for us to connect to. There is no reason to put the Browse Security Info button on the page at all unless we've identified the UUID from the KB."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Why `2` in this and others?"
    },
    {
      "prediction": "I don't think this is the right thing to use.",
      "reference": "This may cause a new allocation, please consider merging the concat in above line. Same applies to change in dotnethostmanager."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Alternatively (and better) would be to look for the .level attribute of the node. If it's bigger or equal to 1, than that is a relative import. So \"from . import x\" should have level 1, while \"from .. import z\" should have level 2 and so on. The same should happen for \"from .c import z\"."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Btw. this API must definitely change with PMD 7 - we are exposing here a implementation detail (that we use Saxon). And it happens, that the way, how custom functions are registered, changed with Saxon 9.5... which makes the need for a implementation agnostic API relevant..."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string.",
      "reference": "nit: `Additional configuration used while sending notification to external services.`"
    },
    {
      "prediction": "I'm not sure if this is a WebDriver instance.",
      "reference": "This should only be sent if the driver is speaking to a W3C conformant remote, so we need an if-condition check like we have in the Python bindings."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "This should have failed before."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `paych.State` field.",
      "reference": "the paymentchannel dir is where the paymentchannel manager will live. it will store the types below."
    },
    {
      "prediction": "I'm not sure if this is a standard command name, but it's not a standard command name.",
      "reference": "This is Safari specific and should be defined somewhere in the `safaridriver` namespace"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "assignments should only be cuddled with other assignments (from `wsl`)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "prefer changing the signature by adding params to the end, not the middle, I think."
    },
    {
      "prediction": "I think this is a bug in v1.ServicePort.",
      "reference": "I guess we aim for hardcoded port for Prometheus operated ports right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is the same effect as doing `node.parent.fromlineno` but avoids the `StatementMissing` exception from calling `statement`."
    },
    {
      "prediction": "I don't think we want to use `--mb_id` here, but I don't think we want to use `--musicbrainz_id` instead of `--top_artist_limit`.",
      "reference": "I think user-ids might be better; also note that options should use - and not _ to separate words. Also, how are more than one id specified? comma seperated? I think the usage statement should indicate this."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "This code is necessary. It makes sure that you can sleep for longer durations than the timer supports."
    },
    {
      "prediction": "I'm not sure if this method is called with a single executor service. I'm not sure if this method is called with a single executor service. I'm not sure if this method is called with a single executor service.",
      "reference": "Can we add the new name in parallel and deprecate this name? We should be careful about changes to the public API and give people at least a release to switch over before removing public methods."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If you're going to start testing that impl itself is not NULL you should probably be doing it everywhere."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`ctx` is unused in LoadPlainYAMLManifests"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "why is this called toBuilder when the method is called fromBuilder? (I realise you did not change this...)"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "nit: seems rather large."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I think it'd make sense to only calculate time.time() once (it's also used if max_ts and min_ts aren't set)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Use existing `grpcStubCallString` instead"
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "In a recent PR, Bob added a `TracerConstants` class. Do you think this makes sense to put in that class instead so that we can consolidate?"
    },
    {
      "prediction": "I'm not sure if this is the case where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state where we're in a state.",
      "reference": "I want to propose couple of different names for catchpointWriting: syncInterruptedWaitingCatchpointWriting syncWaitingForCatchpointWriting catchpointWriting is lacking context, and I found it difficult to understand the logic without this context."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Do you still need the `name` in the arg description, if this is not `str` type anymore.?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We may raise a warning."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Trailing comma caused the eslint test to fail"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think you should use `app.config`. In the usual case, the config file is not overwritten, there is additional config file outside of the source of `Invenio`."
    },
    {
      "prediction": "I'm not sure if this is a trusted issuer, but I'm not sure if this is a trusted issuer. I'm not sure if this is a trusted issuer. I'm not sure if this is a trusted issuer. I'm not sure if this is a trusted issuer. I'm not sure if this is a trusted issuer. I'm not sure if this is a trusted issuer. I'm not sure if this is a trusted issuer. I'm not sure if this is a trusted issuer.",
      "reference": "Will you please update the copyright message to now include `2021`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Potential subscript out of range."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "please undo this change. you didn't really meant to make it, right ?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `path.resolve( __dirname, '../dist')` instead of `path.resolve( __dirname, '../dist')` instead of `path.resolve( __dirname, '../dist')` instead of `path.resolve( __dirname, '../dist')`.",
      "reference": "To check! are these millseconds or seconds :thinking: The docs aren't clear"
    },
    {
      "prediction": "I think this is a bug in multiuploader.",
      "reference": "Why was this moved?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "What are these object with suffix Expansion?"
    },
    {
      "prediction": "I don't think this is the default value for `--rpc-allow-unprotected-txs` and `--rpc-allow-unprotected-txs`",
      "reference": "This breaks backwards compatibility, so it will have to wait for the next quarterly release of the default is to deny. I would recommend adding the flag with the default to allow and then at the next quarterly release rc cycle flip the flag to deny."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the team policy.",
      "reference": "I'm kind of surprised this doesn't require `typename`?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think this will break the case (you can try even with /usr/bin/bison as value): `YACC=\"/path/to/bison -y\" ./configure` I wonder if we should use AC_PROG_YACC at all or simply use AC_CHECK_PROGS since we want to use bison and not another yacc"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "can we explain to users in the docs what happens if they leave the field blank?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We try not to change the function footprints unless absolutely necessary. Why is it necessary to have both secuirty_group_ids and security_groups?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Thanks! We're already replacing File.separatorChar with '/' in the call to FileUtil#toCanonicalPath above, so the correct fix here should be: `relativePath.replace('/', '.')` I'll make the change upstream."
    },
    {
      "prediction": "I'm not sure why this is a class, but it's not a class.",
      "reference": "It could be nice to be explicit about this change in upgrade notes, what do you think?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "spotted a bug."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We were always using 0000000 prefix"
    },
    {
      "prediction": "I think this is a bug in nebula.",
      "reference": "Here we also need to determine if gJobMgr has called the init function."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "Out of curiosity, why is `condition.any?` also necessary here?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Always use `std::make_shared` whenever possible, it will save you one memory allocation."
    },
    {
      "prediction": "I'm not sure if this is overridden.",
      "reference": "Update to real tag before pull."
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "Is there any better string that only exposed by prometheus? We have changed the meter tags to contain method and service name. For example `scrape()` contains `method=getHealth` and `service=server.internal.health.ITzipkinHealth` which made this test failed.  "
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Adding ICoreLogger here lets us pull this into Core as a strategy"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "why did you change this?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is invalid syntax on 1.8."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This isn't part of the PR, but I can't find in the smarts definition that \"[C][C]\" == \"[C]-,:[C]\" There is a line saying essentially not to specify undefined items (but that's a bracket versus non bracket thing)."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is this required for tuple encoding? This is confusing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does it need to be a member variable? It is currently only used in one method."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "@MrTimscampi doesn't this need an update to apiclient?.."
    },
    {
      "prediction": "I think this is a bug in X86_64.",
      "reference": "This is a nop: prob best for history to not change the line"
    },
    {
      "prediction": "I'm not sure if it's called twice. I'm not sure if it's called twice.",
      "reference": "Can you delete this whole file now?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can you combine this passing test, code, solidity binary into existing ArrDelete? the function is much similar, pushing int value into an array, and delete one item in the array"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "I think that could lead to problems when setting it to not sorted again. In that case, it will not be reset. What about using one single method for the adapter (`setDragDropEnabled`)?"
    },
    {
      "prediction": "I think this is a bug in `ddev start` and `ddev start` and `ddev start` and `ddev start`",
      "reference": "I'd say the error should be an error, not instructions to the user. So error would be something like \"site should be running and is not\""
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Are you sure `v3EndpointIDToContainerName` and `v3EndpointIDToTask` are saved in the state file, can you verify that?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This mutex is never used. Should it be, if users can now make calls into the crypto setup?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Check here for sles-, and i'd prefer a regex since I don't know what an 'include' is going to do exactly. :)"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Should this be `None` instead?"
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "Not sure if the warning message is enough for this time, if the configuration is wrong, java-chassis may need to stop working instead of sending out the warning message to let the admin know about it. BTW, we may need a default override policy here."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I see this getting unwieldy as we add more commands with subcommands. Can we perhaps enhance it to handle subcommands properly? Perhaps something like `\"etcd-snapshot:1\"` which would indicate that the etcd-snapshot command may have 1 subcommand after it, and if the 1 next argument after it doesn't start with `--` then the args should be appended after that subcommand."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "why returning a string instead of a list?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Was there a reason for changing all these integration names?   Are they actually used for anything besides information in logs?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "we should not resurrect this method that we just removed"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `save_screenshot` method.",
      "reference": "This needs to be just return self.get_screenshot_as_file(filename)"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "Shouldn't this return false here?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should have json tag"
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "Is this needed after all? Looks like the struct was re-defined inside the test file."
    },
    {
      "prediction": "I'm not sure why this is the default behavior.",
      "reference": "I think the name of the method should match the name of the action: `removeReachableFiles`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "can you make the C in Consent lower case to match the other ones in this list?"
    },
    {
      "prediction": "I don't think this is a bug in iotex-core.",
      "reference": "fix the group"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Prefer `Stream.anyMatch` instead of iterating over all slots."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "we have `logging.TestingLog()` that should be used for that purpose."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is also a question of style. src[i] will always be valid because of check if 'for' statement"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why change it?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `theme.colorStyle` or `theme.colorStyle`?",
      "reference": "nb: this change is unnecessary"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Is the publicLink mostly empty? I'm just wondering how much this will bloat memory usage as sometimes rclone has millions of Object~s in memory."
    },
    {
      "prediction": "I think this field is not a field on the DER encoded CSR. I think this field is not a field on the DER encoded CSR.",
      "reference": "I don't think the Internal API types need the json annotations. They are never serialised, right?"
    },
    {
      "prediction": "I don't think it's a good idea to do this.",
      "reference": "Maybe this was added incidentally. We don't need this function in the interface."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Is this a safe/reliable way to split the URL?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "do we also need to profile the time to getConnection()?"
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's a string.",
      "reference": "Should we move the decode part directly to the actual first-use of this? Or how does this affect if the value gets decoded and we need to get the bytes back later?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "How would you feel about continuing to point this at the MyResearchController's holdsAction, but instead changing that action to force a redirect to the new holds-list route? That way, people will get sent to the new URL instead of having two different URLs that do the same thing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think if yo use %s then you do not need reason.String() and can just do reason."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Having \"wf\" prefix doesn't make sense anymore. Please remove."
    },
    {
      "prediction": "I'm not sure how to use `sinon.spyAll`?",
      "reference": "Removed this copy of the `spyAll` function and replaced it with the same function declared in `helpers.js`. Same for `sortAttributes` below"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Default max cpu should be 8 and memory 64GB"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `nbytes` property. I don't think this is the right thing to do with the `itemsize` property.",
      "reference": "@itholic, can you remove `nbytes = unsupported_property('nbytes')` at `_MissingPandasLikeSeries`?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "What happened to the assertion on `conf.TaskCPUMemLimit`?"
    },
    {
      "prediction": "I'm not sure why this is the default value for `createRef`?",
      "reference": "Just curious: Is using `Object` faster than a literal `{}`?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "How come we don't allow this to be configured with the ACME issuer? Happy to leave this as-is for now if there's a lot more consideration that needs to be made, but it seems like we could/should be able to allow this?"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Should we remove the `Aliases` field as well?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "what's the effect of turning these two off? is there an issue on file for context?"
    },
    {
      "prediction": "I don't think it's a good idea to use `gcloud-latest` instead of `gcloud-beta-latest` instead of `gcloud-beta-latest` instead of `gcloud-latest` instead of `gcloud-beta-latest`",
      "reference": "The format like gcloud-beta-prod is a bit hard to understand. Maybe find a a more clear way to describe it,"
    },
    {
      "prediction": "I think this is a bug in OpenTelemetry.",
      "reference": "Are we renaming this too in a follow up PR?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "The indentation on this is off by one space to the left"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I guess nothing is wrong with this approach, but more curious if you didn't just go `|| (format != VK_FORMAT_UNDEFINED)) {` As if there ever was another external format system added in Vulkan it would need to be manually added here"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `stream.Collectors.joining` package.",
      "reference": "Is order really irrelevant here?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "I think this import will be unused now. If it is unused remove it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Let's change to tx"
    },
    {
      "prediction": "I'm not sure if this is the default block type.",
      "reference": "Looks like I was wrong about the sync cache size being 15% before. There seems to be some reporting bug related to my use of the sync cache, that makes the limit different from the working set cache limit. For now, I say we keep this at `0.10` (change the param default too), and we can change it later if needed."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think it'd be a good idea to define the environment variable name as a constant in values.go because it's hard-coded in several places, but that's a small point."
    },
    {
      "prediction": "I'm not sure if this is the right thing to add indexes to the classifications table.",
      "reference": "Style/SymbolArray: Use %i or %I for an array of symbols."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Our habit is to go ahead and put a description line (or more) in front of every function, not just non-test or exported functions."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "I'm slightly concerned about this because doesn't ORCID use XML instead of JSON?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "brackets around if conditions isn't really pythonic."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "It turn out that when we close server it closed underlying listener itself, so this line always generated and error."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `objectId?` and `objectId?` properties.",
      "reference": "Looks like this is for debugging? Maybe just remove."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case.",
      "reference": "Same here - this code is duplicated. I think we can just remove the `exists?` method completely from `Criteria` and it should delegate to the context."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm not quite sure that we preallocate memory. Do you have a good reason for that?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "If we have added to s.clients, we could just do the following since if its a route will be ok I think. s.mu.Lock() defer s.mu.Unlock() return len(s.clients) <+ s.opts.MaxConn"
    },
    {
      "prediction": "I think this is the case where the target leader is src_ itself.",
      "reference": "if the targetLeader is src_ itself, it is really need call transLeader function?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Can we remove this featureConfig since you removed in L98 (assuming it is not used else where)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "namespaces in this file need a sorting"
    },
    {
      "prediction": "I don't think this is the default MTU.",
      "reference": "This line should actually be: `if c.KubernetesProvider == config.ProviderAKS && c.Wireguard.EncryptHostTraffic {` because we only need to tweak the MTU like this on AKS."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`get` has an optional second parameter that is the default if the key isn't found."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please also indent the new response line as was done to the existing line above."
    },
    {
      "prediction": "I don't think this is the target.",
      "reference": "Shouldn't need this-> here."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I believe this is incorrect, if I'm not wrong, MESSAGE_TRADE should be used when buying/selling items from NPC's"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Better if you give split[0], split[1], and split[2] descriptive names than using them this much through so many lines of code."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "I know we're deleting this soon but I thought I'd fix it anyway :smile:"
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "I like this, makes it clearer what scope the continuation is in"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "These test checks if the value of the merged cells is correct. Please revert the changes and set `autoWrapCol` and `autoWrapRow` to `false` to the Handsontable instance. This change applies to the entire mergeCells.e2e.js file."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Don't need to clear them - because nobody have data there, also can don't delete buckets - just leave them, new nodes will not have them if remove bucket from buckets.go"
    },
    {
      "prediction": "The \"License\" is distributed on an \"AS IS\" BASIS.",
      "reference": "Similarly, this has only one implementing class"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does it send requests with urlencoded bodies anywhere? I thought it sends only json. Maybe content-type should be `application/json` by default?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I must have forgotten that one in previous PR"
    },
    {
      "prediction": "I'm not sure if this is a test case.",
      "reference": "This test name doesn't really reflect what the test does any more... Then again I'm not really sure what it is testing now - is it actually just testing that FactoryGirl can create records? or does that itself funnel through the rails code so that we're testing rails can create records?"
    },
    {
      "prediction": "I don't think this is the case for the upgrade result, but it's not the case for the upgrade result, but it's not the case for the upgrade result.",
      "reference": "Can this be `BuilderForYAMLObject`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "better use `with mp.Pool(...) as pool:` here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since this is a config problem, BAD_REQUEST is probably not the right response."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "We could probably do 1 sec if we have time, and hence exit early if we have small number of clients. So LB = 60 sec. Grace = 10secs. So 50Sec window, if NumClients < 50, Close 1 every second. Then exit when NumClients == 0."
    },
    {
      "prediction": "I think this is the same as `that_name`?",
      "reference": "can you rename `that_col` to `that_column`?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This is not correct, it will override everything else that is currently in `Widgets`. This file shouldn't be modified at all, we should be adding `components.Widget` in `assets/js/googlesitekit/widgets/index.js`, where the rest of that object is defined. Oh, and there's a typo here :)"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "Each task finished will result in the meta info updated?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `setState` method.",
      "reference": "Quick follow-up @aaemnnosttv, why this and not `.trim()`?"
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "I don't think we should have file-wide exceptions for this rule, let's annotate the individual instances."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "@raprasad you plan to take this \"if true\" out, right?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Could you adjust this to `with open(path, \"rb\"):` here and below? We should make sure that we close all files."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Does this need its own import block or can it be combined with the imports below as in most other files?"
    },
    {
      "prediction": "I don't think this is a problem with the `combine_frames` function.",
      "reference": "It defaults to `false`."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why conditional check is done? As i understand, later both `applyPreflightCorsResponse()` and `allowAllCorsActions()` does the same"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "has not yet exit?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I wonder if the version should be part of the deprecation API. It might ease our future selves while debugging issues =)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We chose `info` in the test code for obvious reasons. Changing to `finest` makes debugging harder and noisier."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This is just a rename..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should probably panic here. I think hashers are contracted not to return errors (and returning \"\" doesn't handle the error)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Aside: this is a confusing name for an interface that contains multiple addresses."
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "We expect to use Bolt::CommandResult for scripts as well?"
    },
    {
      "prediction": "I think this is a bug in RSpec.",
      "reference": "same thing as above inre commas and args?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we validate that this is between 0 and 100?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`HardKiller` doing `os.Exit()` without proper shutting down other dependencies. I think there should be a better approach for this."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Why isnt the return value checked?"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "remove this debug"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should change to a call to `Layer::find_layer_index`, which should be renamed to `find_child_layer_index` and it should return a `size_t` (technically the `difference_type` for whatever iterators are going to be used)."
    },
    {
      "prediction": "I don't think this is the case for the main application executables.",
      "reference": "what is this change about?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Why did we leave the `stderr` param in this case while we removed it from other bake methods?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "This seems to only be used by the server/ca package.... maybe this can live there instead of being lumped into these API implementation helpers?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "hmm.. this is Hacky, the test will succeed in Windows even if you remove the calls to these, right?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `ruby_version` and `ruby_source`?",
      "reference": "should this block be in the file `05_install_ruby.rb`?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "To match outbounds, let's just call this `Unary: recorder`, `Oneway: ...`."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "`string.encode('utf-8')` is more common but I guess this is mostly cosmetic :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Consider logging `r.Url.Path`? Either way, ship it!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this probably should be done lazely only if logic/app call txn in the group. Or even done in LogicSigSanityCheck?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Please move this to `common/enums/defaults.go`."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "In general, if you find unalphabetized imports, you should alphabetize them. Fine for now though."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "we should probably deprecate (and display a warning) the misspelled keyword arg here rather than removing it... and then add the new one. This changes a public API and will break any code that is currently using the misspelled version."
    },
    {
      "prediction": "I don't think it's a compensation_V, but I don't think it's a compensation_V, but I don't think it's a compensation_V, but I don't think it's a compensation_V.",
      "reference": "Is this if statement here necessary? It looks like this is the same logic that is taken care of in the setter for the property \"CompensationVoltage\"."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to make it a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, but it's not a string, so it's just a string.",
      "reference": "Eliminate this function; handled by mappings and analyzer"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the route name?",
      "reference": "I wonder if this new logic would actually fit better as a support method, both for readability and overriding... e.g. <pre> protected function getRouteNameFromDataSource($route) { if ($route === 'collection') { return $this->getDataSource()->getCollectionRoute(); } elseif ($route === 'record') { return $this->getDataSource()->getRecordRoute(); } return $route; } </pre> That's extremely nitpicky, and you can feel free to leave this as-is if you prefer... but that feels marginally better to me."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is in test code: understanding what we're doing is important in this context."
    },
    {
      "prediction": "I don't know how to do this, but I don't know how to do this.",
      "reference": "This change (and a few similar ones below) are not related to rpi3 support, and should be removed."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Hmm, why did we come to need the `,` at the end?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm suspicious of this. For one thing, `query._fields[paths[i]]` may be `0`, `false`, etc. so checking for falsy will catch both cases where both the field isn't in the projection and if the field is explicitly excluded from the projection. For another, I'm not so sure that #6546 is a bug. Let's discuss that more."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is this? I'm a bit unclear why the parser would have a list of statements in it."
    },
    {
      "prediction": "I don't think this is a bug in the prometheus package.",
      "reference": "I believe this is Prometheus name, wonder if this is descriptive enough of a label name? @nrchakradhar @simonpasquier wdyt?"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "Are most of our other fields default-zero-value? Would `AllowVXLANPacketsFromWorkloads` be a better formulation of this? I think it would make it easier for golang users of the API (default value matches the type zero-value)"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "void RemoveTransactions(Address sander, long removeBelowThisNonce) and separate these two calls"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Not sure which interest you are looking for to propagate here, but keep in mind that we have helpers (maybe not in /test package?) to check/wait for interest on a literal on a server for a given account."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "nit: should not need this."
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Since this constant is an implementation detail rather than a user-facing API, is it better to define it in a place where it is used?"
    },
    {
      "prediction": "I'm not sure if this is a list. I'm not sure if this is a list. I'm not sure if this is a list.",
      "reference": "It would be nice if we have some docs explaining this. Core luigi should avoid having hard to understand code."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "extract a method to call from a test"
    },
    {
      "prediction": "I don't think this is the default thread factory.",
      "reference": "nitpick: regular order is private than final."
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "We could add an old names here, the ideal would be to not force to disable missing-any-param when the old one was already disabled. But they are not really equivalent so maybe you were right to not add it."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": ">public const string LINQ = \"LINQ\"; [](start = 8, length = 34) Are there duplicated benchmarks here? #Closed"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Probably worth taking the opportunity to add yardocs to this method now. Esp. curious about what the options hash accepts."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This is Very Meh . We want to get rid of `role_data`, and it's an internal field."
    },
    {
      "prediction": "I'm not sure why this is a `async` method.",
      "reference": "`await this.driver().loadExtension(path);` should work"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is any of this needed anymore?"
    },
    {
      "prediction": "I think this is a bug in ostree-repo-private.h.",
      "reference": "Can you add a mention here and in `ostree-repo.c` that the holes were found with `pahole`?"
    },
    {
      "prediction": "I don't think this is a hack, but it's not necessary to use `query_solr(user_params, extra_controller_params, solr_search_parms_logic)`.",
      "reference": "While we're changing this, I wonder if we can do away with `extra_controller_params`.. Maybe a new type of `solr_search_params_logic` that appends the attributes?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I believe that you only need to rescue Beaker::DSL::Assertions, as they include Minitest::Assertions."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Do we need `&=` or `=` is sufficient?"
    },
    {
      "prediction": "I don't think this is the default, but it's the default.",
      "reference": "Let's keep both of these here. It should work on most any version of Drupal 8 then true?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@lmolkova This ok? I'm getting random failures from the build checks that don't happen locally from a few non-deterministic time related comparisons."
    },
    {
      "prediction": "I don't know if this file is used in compliance with the License, Version 2.0 (the \"License\"); you may not use this file except in compliance with the License, Version 2.0 (the \"License\"); you may not use this file except in compliance with the License.",
      "reference": "Q: are we supposed to change this for files that already exist?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "I count only four times where `selection_specs` had to be specified as a keyword instead of by position! If that is how often it was used that positional argument in our own codebase, I am pretty certain users barely used it (if at all)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "is this test for the case above? seems to cover a numeric rather than empty val?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I like the general idea, but this will break: - JSON is not binary-safe, so anything binary will break this. - JSON is super slow for multiple-MB things - We want to have drag-and-drop upload - the easiest way to implement this is FormData upload, so we should have a multipart/formdata endpoint. Can we put to /flow/content?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "_and_synched seems to be more consistent w/ exited_and_cleaned"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nit: in case of whole file `ifdef` it may be helpful to have `_netcore31` suffix it in the name of the file as well."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `typeMap` property.",
      "reference": "should use Number instead of Long"
    },
    {
      "prediction": "I don't know why this is needed.",
      "reference": "Had no idea that method existed!"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I wonder if we shouldn't just do `w.show()` here, which causes Qt to correctly calculate the sizes."
    },
    {
      "prediction": "I don't think this is the right thing to do with the object_store.key_for_paths?",
      "reference": "may be nice to have helper method to generate s3 paths rather than the minor code dup"
    },
    {
      "prediction": "I'm not sure if this is a `ValidationEngine` instance.",
      "reference": "This isn't needed here, we still run `this._afterAuthentication` which loads settings & config - the reason the settings fetch is here is to make sure we have all the settings before saving the blog title rather than fetching everything once auth has completed. Probably moot anyway as the oauth code will be removed shortly  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This line is getting a little long; let's move the conditions to at least two lines (maybe three)."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Don't use relative paths. src directory is already on the include search path"
    },
    {
      "prediction": "I don't think why this is needed?",
      "reference": "Line is too long. [86/80]"
    },
    {
      "prediction": "I don't think this is the right thing to do, but it would be better to use `File.expand_path('../../../../app/lib/twitter_digits.rb', __FILE__)` instead of `File.expand_path('../../../../app/lib/twitter_digits.rb`, __FILE__)`",
      "reference": "We have to navigate up four directories to come down three? I see it, but it's kinda icky. Is something like `load Rails.root + 'app/lib/twitter_digits.rb'` out of fashion nowadays?"
    },
    {
      "prediction": "I think this is a hack, but I don't think it's a problem.",
      "reference": "Empty space at end."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `with_bolt_executor` method.",
      "reference": "I think similar to line 176 here we'll want to call `detect_project_conflict` after overriding this."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `require('child_process')`?",
      "reference": "How about `const { promises: fs } = require('fs')` and then replacing `fs.promises.` with `fs.`?"
    },
    {
      "prediction": "I think this is a bug in github.com.",
      "reference": "This ignores errors closing the body. Not likely to happen, but no reason to take the risk either."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why was this change needed?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `--import-lockmass-tolerance` option.",
      "reference": "Needs a description added to CommandArgsUsage.resx"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "The line is a bit too long. That's why the test currently fails. Please break it into two lines."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Prefer `Stream.anyMatch` instead of iterating over all slots."
    },
    {
      "prediction": "I don't know why this is needed.",
      "reference": "Can this just be a feature flag to check if it's on? This will give us flexibility on launch date (which could be turned on July 1st) and allow us to easily revert back in case the policy is reverted."
    },
    {
      "prediction": "I think this should be an ADC.",
      "reference": "Due to this change, src/examples/adc needs to be modified"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "`s/singlePointer/singlePtr` or please rename the type to `singlePointer`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we need it? If right now it's toml"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "You are never calling oldUnmount, this could lead to a plugin chain failing."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "What does setting partitionInfo to null mean exactly?"
    },
    {
      "prediction": "I don't think we need to check the length of the new columns.",
      "reference": "Not sure you need the initial ``not_updated`` as ``any([])`` evaluates to false."
    },
    {
      "prediction": "I don't think this is a bug in the database.",
      "reference": "Since this migration hasn't been merged to master yet, what do you think about just squashing these two into the migration you really want?"
    },
    {
      "prediction": "I don't think this is a bug in BetterErrors.",
      "reference": "This doesn't apply to all developers"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think `serializer.xml` can be moved into condition below too"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `dotnet` and `netcoreapp3.1` and `netcoreapp3.1` and `netcoreapp3.1` and `netcoreapp3.1` and `netcoreapp3.1` are the same as `netcoreapp3.1` and `netcoreapp3.1` and `netcoreapp3.1` and `netcoreapp3.1`",
      "reference": "Probably put this in a simple README.md file?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Super Cool bitwise   Minor: Most likely you don't need `System.Collections.Generic`, `System.Linq` & `System.Threading.Tasks`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "If we just return the TCC, maybe we need to update the method name for it."
    },
    {
      "prediction": "I don't think this is a bug in the future. I think this is a bug in the future.",
      "reference": "For consistency, shouldn't this use `SwaggerModeler.GetMethodNameFromOperationId(method.Name)` as above? I'd just reuse `\"Additional parameters for \" + SwaggerModeler.GetMethodNameFromOperationId(method.Name) + \" operation.\"` here, `string.Format` with `CultureInfo` is complete nonsense here anyways."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "As this is just a backport, I guess it is fine to leave these timings, although they are not enough to make tests stable."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why this way?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Changing this because otherwise the second run of testExtractCompilationsEndToEndWithDatabase will try to overwrite a generated file and fail. Maybe there's a better way?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This modification is not correct. Suggections: 1. upgread guava to 30.0-jre will fix this issue"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "All changes to signature code stem from here. The syscalls interfaces expects VerifySignature to return an error. I performed the change here and bubbled it up through the rest of the code - mostly mechanical."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This strategy seems good. Just wondering do you think this is a good time to move stuff out of core? For example, I guess storage, since it's for use by server and not client, doesn't need to be Java 6?"
    },
    {
      "prediction": "I don't think this is the case for partitioned tables, but it's not the case for unpartitioned tables.",
      "reference": "We had a wrong predicate before: we compared a list to an expression."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Name copy-pasted from above. \"empty\"?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `self.norm2_name` and `self.norm2_name` and `self.norm2_name`",
      "reference": "May I ask why change this?"
    },
    {
      "prediction": "I think this is a bug in Datadog.Trace.Agent.MessagePack.",
      "reference": "Does this mean we now always include the dictionaries even if they're empty? If so, we should make sure that this doesn't break the Agent (even older versions). It's possible that it doesn't handle empty dictionaries well."
    },
    {
      "prediction": "This is a hack, but it's not a good idea to change the value of 'FastSyncCatchUpHeightDelta' to 'null'.",
      "reference": "The description and name is unclear. Typo in 'which'."
    },
    {
      "prediction": "I don't know why this is the right thing to do.",
      "reference": "Files should have an extra line at the end of them."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "> i#1312 AVX-512 support: Add code cache to/from context switching. s|to/from|| (redundant and mildly confusing (called \"enter\" and \"return\" in code))."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "This stat may fail, right? I think dag_file_exists does not actually check the file is there."
    },
    {
      "prediction": "I think this should be a function, but it's not a function, but it's not a function.",
      "reference": "I think we can make a safe assumption that if only two values are passed in then you have `(optionsToValidate, optionsForValidation)`, if its three then you have `(optionsToValidate, overrideOptions, optionsForValidation)`"
    },
    {
      "prediction": "I think this should be a bit of a hack.",
      "reference": "If there are more items to add to what's being written out here, please add a TODO."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `cmsg_data` argument.",
      "reference": "Can you add an `else:` case to handle an invalid length? That will prevent weird errors."
    },
    {
      "prediction": "I'm not sure if this is the right place.",
      "reference": "* We need to deprecate/internalize first on master. * We should directly make the AST node final now * The setter `setName()` can be package-private."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Where did this functionality move to?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "maybe should firstly check whether current tidb support `split table region`?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `googlesitekit/datastore/user/constants.js` or `googlesitekit/datastore/user/constants.js` or `googlesitekit/datastore/user/constants.js`?",
      "reference": "Please use the same (plural) name for the new component since it renders multiple notifications."
    },
    {
      "prediction": "I think this is a bug in the catchup service.",
      "reference": "Perhaps show attempt x of y in message ie: Failed to download block %d (attempt %d of %d). %v"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "why did you took `Exception` out? Is this method only throwing runtime exceptions?"
    },
    {
      "prediction": "I'm not sure if `boost_from_average` is set to `TRUE`.",
      "reference": "please revert all of these unrelated whitespace changes"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "PGP_INLINE is clearer IMHO"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Please group imports"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Would it make sense to expose this as a config option in `TestHiveMetastore`? A small number of worker threads helped us to catch a few connection leaks early on."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `dilation_h` and `dilation_w` and `dilation_w` parameters.",
      "reference": "Let's fix the extra spaces above."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "should a similar change be done for findElement?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "// Keys are stored in an in-memory map, where the key is the name of the // private key, and the value is the structure where the actual private key and the password are // stored."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "I think this needs a json inline tag here"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Hi @cjimison good point but doesn't this break the compatibility with Erlang/OTP prior to 17.0? I think this could be done over an conditional macro defined in the rebar.config: `{erl_opts, [ {platform_define, \"^R\", pre17} ]}` and some additions with `-ifdef(pre17). ... -else. ... -endif.`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we change/wrap the error?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Are we sure that passing this log in warning does not risk spamming the logs of a node running on the mainnet or on ropsten etc ? Do we often receive invalid messages of this type ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'd like to avoid a method call here atm since this is an extremely hot line in the code."
    },
    {
      "prediction": "I don't think it's a bit of a hack, but it's a bit of a hack.",
      "reference": "Is this a bugfix?"
    },
    {
      "prediction": "I don't think this should be a list of strings.",
      "reference": "Is this a relevant change?"
    },
    {
      "prediction": "I think this is a bug in JUnit5.",
      "reference": "@dansanduleac what do you think of this one? dots were aligned and no longer are  "
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why we dont delete app specific notes when app is deleted?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do here.",
      "reference": "The _OverviewPlugin_ is forcefully enabled without the option to disable it, using _PluginDescription.alwaysEnabled_. That should also work for this plugin?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Can you facet on this new externalStatus Solr field?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I wonder if it would it make sense to push the pivot facet handling down into `FilterField` (or maybe a subclass, `PivotFilterField`?)?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Ah I see what you were saying about making it harder to validate types. We'll have to catch the return for that."
    },
    {
      "prediction": "I don't know why this is the right thing to do?",
      "reference": "Try using using `.setDismissOnTouch(true)` instead"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the scope?",
      "reference": "Zach, is `UpdateSpan` of concern too? I see that it is called from `ExecuteAsyncInternal`."
    },
    {
      "prediction": "I don't know how to use `TypeConversion`?",
      "reference": "Nit: its scope can be reduced to package default"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Why is this get;set;?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we also create sender resources for unicast locators? Should we make a similar change on StatelessReader?"
    },
    {
      "prediction": "I think this is a bug in Datadoghq.",
      "reference": "Can we use `dotnet` instead of `net`?"
    },
    {
      "prediction": "I think this is a bug in Datadog.",
      "reference": "Should this be `ForceFlushAsync`? Given we have the `async` suffix elsewhere."
    },
    {
      "prediction": "Should we remove the file?",
      "reference": "Is this change intentional?"
    },
    {
      "prediction": "I don't think this is a bug in Sarif, I think it's a bug in Sarif, but I think it's a bug in Sarif, but I think it's a bug in Sarif.",
      "reference": "This could be an integer property if we supported explicitly setting non-string-valued properties."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is not consistent with the previous annotation - is it because of the usage in `Admin\\Content\\Category\\list.html.twig` twig template? Should not it be at least mentioned in the commit message? :slightly_smiling_face:"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "why add `return` here?"
    },
    {
      "prediction": "This is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "put this hash in variable"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why not use `kbfsblock.ZeroRefNonce`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "what mypy warning does this address? I'm confused by this change."
    },
    {
      "prediction": "I'm not sure if this is the last attacked.",
      "reference": "Note that `hasAttacked` that is called before this function already performs this check. You probably don't need to check `hasAttacked` then."
    },
    {
      "prediction": "I think this is a hack, but it seems that the `raw-loader!@salesforce/design-system-react/components/carousel/__examples__/default.jsx` plugin is not available in the `raw-loader!@salesforce/design-system-react/components/carousel/__examples__/default.jsx` plugin.",
      "reference": "Unfortunately, the site example only has access to imports from `components/index.js` that means that you can't import the items file `carousel-items.js`. You can import that file in all the other storybook files though."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Leave this out and move the script to the scripts folder."
    },
    {
      "prediction": "I'm not sure if this is a WebDriver instance.",
      "reference": "This should only be sent if the driver is speaking to a W3C conformant remote, so we need an if-condition check like we have in the Python bindings."
    },
    {
      "prediction": "I don't think this is the default behavior.",
      "reference": "TransferFormat.Text in general purpose connection interface? :/"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `executable_path` or `executable_path`?",
      "reference": "Is this `@missing_text` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This work for both sides?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `i18n` and `lodash` modules.",
      "reference": "`lodash` shouldn't be grouped under WordPress dependencies"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Include the standard parameterized error tests as well."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "All lowercase in route rule."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "I'd suggest we use `response.profiles[ 0 ].webPropertyId` here instead, to make sure it's based on the profiles retrieved. The value _should_ be the same, but I think it's a bit more accurate like that."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This doesn't change the default of 6h, but will increase the displayed timeframe by 3h for each long press, before wrapping around to 3h. This requires 7 long-presses - quiet a journey ..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We still need to figure out a way to get rid of this write method. Is this still necessary?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`assertItemsEqual` compares the sequences after sorting them, is that intended?"
    },
    {
      "prediction": "I don't think this is a bug in Selenium.",
      "reference": "I don't think this one needs to be changed since the only previous path is already an absolute one."
    },
    {
      "prediction": "I think this is an ARMServiceDefinition?",
      "reference": "what's the goal of this?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "why is this here? We already have a message pool in the node."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Another mess after all renames and enum conversions. Doesn't break anything though."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think it's necessary to change this for the history plugin tests?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "In general, I suggest using the `kind()` getter inhereted from `TransportInterface`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is the removal of `[AppDomainFixedOutput]` on purpose? (looks like a copy-paste...euh..remove error)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "AWS Identity and Access Management (IAM)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "gofmt everything pls"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "ditto, We do not need add this feature for PodXXXChaos"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "There is a simpler way to do this: 1. Don't bother with the whole lowerCamelApiTypeName in SampleConfig 2. Use this code: `return localVarName(Name.upperCamel(apiTypeName, \"Service\"));` Basically, each of the static creation methods of Name just need to have their arguments all be in the same casing, so you would just pass the upper camel string \"Service\" here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you explain this change to me?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "let us rename the artifact to `storageclass-single-replica.yaml`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Nit: I should have done this before, but rename the file to LibuvFunctions.cs. Make sure no other files are misnamed."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "We should not add new types unless absolutely required. I'm not sure `UUID` is requires a new type"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If only Gatling uses it, can we skip introducing new entity for now? Looks like overkill..."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "rename -> info ?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the config.",
      "reference": "Remove the `config_path=dict(...)`, that is automatic!"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I had to create a new flattened tree to support this functionality. The only other place in which a flattened tree is created is during the audit itself. Since `axe.cleanup` can be called at any arbitrary time, we can't reuse the same tree."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "As this method is just set the internal cofigModel, it's better to use setConfigs instead of addConfigs."
    },
    {
      "prediction": "I'm not sure why this is the right value for the timeout.",
      "reference": "Is this line needed?"
    },
    {
      "prediction": "I'm not sure if this is a bug in knative-gcp.",
      "reference": "nit: import formatter"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `x-nullable` property, but it's not the right thing to do with the `x-nullable` property.",
      "reference": "can you use LINQ's `All` instead? Should be a side-effects free one liner with that."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Could you please remove `#include <spawn.h>` as a whole and see what happens? I believe that this is no longer needed; it was necessary when we called `posix_spawnp` directly, but now we use `h2o_spawnp`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "`whether this resource is paused` to `whether this resource has been paused` ? To keep same doc style."
    },
    {
      "prediction": "I don't think this is the right thing to check.",
      "reference": "This method is validating permission for hp flow. Can you please rename this method to convey the same?"
    },
    {
      "prediction": "I'm not sure if this[kBeforeHandshake] is set to true.",
      "reference": "Just to confirm, do we actually want to explicitly set the `kBeforeHandshake` symbol on all network errors regardless of whether the options/property is passed in?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "How soon after this will Apply() be called? It would be a shame if there was still a significant delay before a missing or superfluous route was corrected."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "While this is commonly correct, the more reliable check is to get the package's identifier from the type checker and check those for equality. The information should be there, just another matter of plumbing it."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Just to clarify, should this be 'composite_root/root/' or 'composite_root/'?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Any reason not to move it to after line 281? These are all pubsub related fields IIUC."
    },
    {
      "prediction": "I think this is a `Number` primitive or object. I think it is a `Number` primitive or object.",
      "reference": "Checks if value is a negative `Number` primitive or object. Zero is considered neither positive nor negative."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Just a nit, but remove the empty line here. :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "A `GoPackageInfo` details message should be added to the `CompilationUnit_FileInput` to ensure the import path remains the same."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Please don't create new fields with the `m` prefix. I'd rather mix than introduce more of these."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we please simplify these names? they are awfully verbose and repeating the parts that are already unique and obvious."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Flipped the logic here, was this actually wrong before?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "I think (a) should be initialized to `NAT_FE_LOOKUP_ALLOW` and (b) it should be probably the first thing in `calico_v4_nat_lookup2`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `extends LuceneTestCase` here, but I'm not sure if this is the right thing to do with the `extends LuceneTestCase` here.",
      "reference": "I'd look as to what this class actually does... seems weird. Classpath below (under \"run\") is wrong for gradle."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Group w/ algorand imports"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "I don't think this import is being used."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is an interesting way to do this. I like it. An alternative way to implement a multiple kind pattern was to have this return `AnyKind` and then have match perform an actual check to see if it matches."
    },
    {
      "prediction": "I think this should be removed in 2.0.",
      "reference": "You did not check this code"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This was necessary due to a bug uncovered in testing. If an actor method which requires params is called without any params at all, not returning an error here causes a panic."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Thanks for the pr. Would you be able to edit the file to use spaces rather than tabs? Normally we have prettier run on commit, but I guess file patches don't do that."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is it intentional that we removed this annotation?"
    },
    {
      "prediction": "This is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "should be general?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "if lowest inserted header is non null non zero then pivot should be higher and a better best known on the left. maybe Head?.Number ?? Math.Max(Pivot, LowestInsertedHeader))?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is a FakeApp class needed? Can test use a Mockito mock instance instead?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `is_constant` flag.",
      "reference": "We should make this an enum."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "@lgolding, note I fixed the forward slashes that appeared in the VS output (which was certainly not by design)."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Minor unrelated fix that snuck in."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do with it. I'm not sure if this is the right thing to do with it. I'm not sure if this is the right thing to do with it. I'm not sure if this is the right thing to do with it. I'm not sure if this is the right thing to do with it.",
      "reference": "Took the opportunity to fix the import ordering."
    },
    {
      "prediction": "I'm not sure if this is a string, but it's not a string.",
      "reference": "I think int and float can be handled in one if statement. The subsequent calculations don't really care whether it si a float or an int."
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "Can we keep this at 10 to reduce the probability of a flake? Or are you afraid this would be too likely to give a false positive if delayed cancellation is every actually broken?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `gcsblob` and `gcsblob` and `gcsblob` and `gcsblob` and `gcsblob`?",
      "reference": "nit: add a blank line under this."
    },
    {
      "prediction": "I don't think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "no need to add this flag query the endpoint set-up to determine the chainID"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Here is a few scenario - What if there is a submit button with in a form, but is always disabled?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "wrong code: should be `Wh_e`"
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "This leads to a small \"leak\" (mostly theoretical only though), if we don't want it this could be created in `initialize()` and destroyed in `finalize()`."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "BuildIDOSEnvVarName or similar, otherwise it sounds it's actually holding actual value of env var"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "I like this standard \"container has started\" message. Should we have a \"container exited because FOO\" message as well?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "And again. The reason it's bad is that if someone uses a JDK not produced by Oracle they won't have this class."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We have Vue application at our disposal, and have examples container implemented as component. Shouldn't helpers be imported instead being global? Not the best practice in Vue app I guess"
    },
    {
      "prediction": "I think this is a bug in the error interface.",
      "reference": "No trailing punctuation in the error message."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "tested? seems like it could break"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This have to be public because the renamed o.a.l.backward_index.TestBackwardsCompatibility refers this."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "unrelated to your change, but I don't think that this is correct anymore. We also seen to remove application support from `primaryNodeUnupgradedProtocol` for the test to be correct."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should this also validate that the RoleArn env var is provided, or just let the creds fail?"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "fwiw, in tchannel-go I've implemented a similar method on TChannel that either returns a Tracer instance it was initialized with, or returns `opentracing.GlobalTracer()`, which by default happens to return a singleton instance of `NoopTracer`. In Go the use of global variables is not frowned upon as say in Java, so this pattern allows minimal work to enable tracing in a service, one just needs to store a real tracer in the global variable, e.g. via `opentracing.InitGlobalTracer(someTracerImpl)`, while the instances of TChannel do not need to be explicitly given any tracer since they will default to that global."
    },
    {
      "prediction": "I think this should be a hashable type, but it's not a hashable type.",
      "reference": "Shall we also add `ks.Series([1, 2, 3], name=[\"0\", \"1\"])`?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Can this be updated?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "this change is to avoid duplication on the defaults. They are already on the Configuration class. (Also I removed the false default, because the admin format does not have it). This is also produces the rest of the diff, changes from false to null."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What does it protect from? If it's subsequent CNI calls, won't containerID be different from the first one? or it's different in containerd? we use `getInfraContainer` to get the lock identity in CNIAdd. And this reminds me what if the first CNI call and the subquent ones run into connectInterfaceToOVSAsync, will duplicate ports being created or it has been handled?"
    },
    {
      "prediction": "I'm not sure why this is the right place for this class, but I'm not sure why this is the right place for this class.",
      "reference": "In Exceptions' constructors, we always add a optional last parameter `Exception $previous = null`. In the past, this was (still is?) a part of the coding standards."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case.",
      "reference": "I think more idiomatic (and consistent with elsewhere in our code base, and more natural to read as \"25 seconds\") is `25 * time.Second`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Enabling `YAML` by default would be a breaking change in behavior for some applications if the struct's used by that application already include YAML tags, but their application has been (un)marshaling DynamoDB Attributes based on the struct name."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "For the command executor, which in turn, uses the HTTP client to talk to the WebDriver, the client might have high-timeout values set, so the shutdown can take a long time if we wait for it to complete, especially if multiple-long running threads are there. I think it might be a good idea in general to couple the shutdown() with `awaitTermination()` with a timeout, if the ongoing tasks do not complete within that timeout then call `shutdownNow()`. What do you think?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this change needed? `start()` is still defined and uses `HiveMetastoreTest.class`. The only difference is that this doesn't pass a `Configuration` and the parameterless `start` passes `new Configuration()`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think it is weird to store sr in protocol struct"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Will this cause a reload _all_ NATable information? It's too bad we don't have some way to limit the reload to just the tables that have a metadata mismatch."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "'fail unless X is a non-zero number' it will also fail if X is a byte string"
    },
    {
      "prediction": "I'm not sure why this is a bug in the holoviews library.",
      "reference": "SyntaxError I think"
    },
    {
      "prediction": "I think this is a bug in VkLayerTest.",
      "reference": "I've filed an internal spec issue to add these missing VUs."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Can you please revert changes to files in the `thoughtworks` package? This is legacy code and we will eventually phase out RC."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "In iceberg, we usually don't use `*` to import package, it's more clear to import the specify package one by one."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "And again. The reason it's bad is that if someone uses a JDK not produced by Oracle they won't have this class."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the timeout control.",
      "reference": "Since we now keep track of all bytes written, and extend the write timeout as needed, it's tempting to no longer add 2 times the max buffer size to the bytes written accounting for the connection drain timeout. As we've discussed before, this add several minutes to the timeout with the default 240 bytes/sec rate limit. I'm thinking instead this line changes to `timeoutControl.BytesWritten(minDataRate, 1);` to add a grace period to the drain if necessary. What do you think @Tratcher?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `formPropsSet.has(key)` and `formPropsSet.has(key)` and `formPropsSet.has(key)` and `formPropsSet.has(key)` are the same as `formPropsSet.has(key)` and `formPropsSet.has(key)` and `formPropsSet.has(key)` and `formPropsSet.has(key)`.",
      "reference": "Good call. Makes we wonder if we should do this with the ARIA props."
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "Please do not use wildcard imports."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the wlr_surface_create() function.",
      "reference": "Not sure about these added logs, as said in the commit message it's probably not something we want all the time, but it helped me debug a bit."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should there be an equivalent check or is it ok to remove this comparison?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "sorry, why this change?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "I think best practice is to use `NamedList<Object>` as the return type, and `NamedList<?>` as the argument type in methods, but I can't find a reference for it right now."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Be careful, the base model is imported here !"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Do we want to make this part of the default? Probably not. In fact, the default should probably be eth, web3 and net (which are the standard namespaces on other nodes)."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with `code_set_id` and `code_set_id`?",
      "reference": "What is the plan when we deploy the Crawler VM project and eliminate the Clump model?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "these two are customized config fields, if we don't need them any more, we probably can use default ControllerManagerConfiguration"
    },
    {
      "prediction": "I don't think this is a good thing to do with the `runtime.Compiler` parameter.",
      "reference": "I don't think we should be pulling the runtime name from the Compiler. There are two compiler frontends, but both of them compile the same source to generate the \"go\" runtime. I think until there is a request from an alternative implementation (the embedded world **might** have a different runtime), it's fine to hardcode this as \"go\""
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `this.schema.options.discriminatorKey`",
      "reference": "fields may be an object."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "i'm not confident these are the right defaults... anybody have input?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "DiskGroupList can be better name"
    },
    {
      "prediction": "I think this should be a function that returns `nil` instead of `nil`.",
      "reference": "nit: lets leave gateway options at the end of the func signature."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "It will be better to use `commit()` on a separate thread, apart from the UI thread. The reason is `commit()` is synchronous while `apply()` is asynchronous. So in case it might not perform actions immediately as expected."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "Took me almost 4 hours to find this."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "There should be only a single blank line between imports and `__all__`."
    },
    {
      "prediction": "I think this should be a test case.",
      "reference": "Doc size increased by 1 since _root_ is also returned by queries."
    },
    {
      "prediction": "I don't think this is the right thing to do here. I don't think this is the right thing to do.",
      "reference": "Now the return value has changed (or at least now includes `clip`) it might be worth updating the docstring..."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "shadow: declaration of \"err\" shadows declaration at line 410 (from `govet`)"
    },
    {
      "prediction": "I think this is a better way to do this.",
      "reference": "Should we be escaping $attr and/or $value here? Seems like htmlspecialchars() might be in order to be on the safe side."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "why not remove the need for the `quiet_o` method and just add it similar to how the `--branch` is added? also, looks like the indenting is a little off"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is the case.",
      "reference": "These variables are already created in constants. Please reuse those."
    },
    {
      "prediction": "I don't think this is the case for the `version_id` parameter.",
      "reference": "query_args is a string, not a list. Therefore you cannot call append to it. Also, line 986-989 of key.py already have code that is appending the versionId query parameter."
    },
    {
      "prediction": "I think this should be a better way to do this.",
      "reference": "I think this change and the one below will break the integration tests which expect a `nil` object if `NewObject` fails."
    },
    {
      "prediction": "I don't think it's a string literal, but it's not a string literal.",
      "reference": "Looks like this isn't used in this file?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why hidden name? How about `index_name`?"
    },
    {
      "prediction": "HiveScanSpecialMode should be set to 0.",
      "reference": "Usually, CQDs are not accessed directly in executor operators directly. It should be passed as a flag in the TDB. It is possible that the query is compiled in a different process, then this CQD setting won't be available in the executor layer."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This tag was broken, the value write to log was the memory address. Please verify that this actually write out meaningful content in log."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why do you have to disable all of these checks?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Just a note to myself: After merging this, I should edit the line after this one to use `message.error`, as raising a `CommandError` from here seems wrong!"
    },
    {
      "prediction": "This is a hack.",
      "reference": "In this test, we want xax to be dead, so that aflags are not spilled to a slot."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I remember there were some misleading code about this but forgot to correct them. Although we initialize `config` here, it was discarded in `complete`, so I guess setting the default value here doesn't take effect. We should change L139-L140 as well to use the initialized `config`. So do antrea-controller."
    },
    {
      "prediction": "I'm not sure why this should be used.",
      "reference": "Stubbin a value object (like `RSpec.configuration`) is a bit of a code smell, I think. You can just set `color_enabled` and `success_color` through the configuration APIs provided by `RSpec::Configuration` -- no need to stub. The `sandboxed` thing in `spec_helper.rb` takes care of preventing changes to the configuration object in one example from leaking into other examples."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "you can use `toString(true)` that will work for BTC and remove the prefix for BCH."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This line is too long now - please break it after the comma."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I find this addition to the interface a bit contentious. I think it would be cleaner to just return the response headers together with the new stream on `NewStream`. I.e. change the method signature for `NewStream` to be: `NewStream(ctx context.Context, overlay swarm.Address, headers p2p.Headers, protocolName, protocolVersion, streamName string) (p2p.Stream, p2p.Headers, error)`. I'd like to hear what other think. cc @zelig @janos"
    },
    {
      "prediction": "I'm not sure why this is the case.",
      "reference": "i hope there is some magic where isEmpty or some cron can strip all non listable products from cart, but since we have the situation tested it should be OK and also we'll see during tests"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think we should check the type returned by `getLiteral` and handle that here. Then we won't need separate code for different versions."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Tests for JWT handler functionality?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "It's weird to set a 101 response and complete without writing anything, but this is still a valid test case right?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we move that information in the capability itself?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `_auto_indexable_1d` flag.",
      "reference": "Is this needed?"
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "This log should not be an error as it communicates that we need to retry till we get the cert information for remote ingress controller."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "BlockTree alredy has a polluted API, this one seems very internal"
    },
    {
      "prediction": "I'm not sure if this is a test.",
      "reference": "Sorry, I realize my line numbers were probably off after you deleted your variables! I meant for this to go in the `before(:all) do` and `after(:all) do` blocks."
    },
    {
      "prediction": "I think this is a hack, but I don't think it's a better way to do this, but I don't think it's a better way to do this.",
      "reference": "This bit I wasn't really sure about."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "From the code, a check's metatdata was only added to `axe._load` if a rule used it. Since `role-none` and `role-presentation` were no longer used in any rule, their metadata was never added. This caused any translation file that passed translations for those checks to fail `axe.configure` with > \"Locale provided for unknown check: \"role-none\"\" To fix I added this line to parse all checks regardless of if a rule uses it or not."
    },
    {
      "prediction": "I'm not sure if `meta` is set to `None` or `update_policy` is set to `incoming`.",
      "reference": "We should raise `ValueError` if `update_policy not in ['existing', 'incoming']`. (or `in Enum.__members__` or however we want to express legal values)"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "`_applicationDelegate` and `_window` are already set in the call for `: this (applicationDelegate, window)`, no need to assigning them again here"
    },
    {
      "prediction": "I think this should be a function.",
      "reference": "We might not have a selector prop in the consumer"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "IMO == true is more readable than ?? false"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "feel free when editing sections like this to introduce modern features like object destructuring."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think the correct pragma is `# -*- coding: utf-8 -*-"
    },
    {
      "prediction": "I don't think IEC_104_IANA_PORT is the default value for IEC_104_IANA_PORT, so IEC_104_IANA_PORT is the default value for IEC_104_IANA_PORT",
      "reference": "This fixes some import errors, due to the fact that this file has the same name than its module."
    },
    {
      "prediction": "I think this should be a `sync.RWMutex` and `sync.RWMutex` and `sync.RWMutex` and `sync.RWMutex` is a `sync.RWMutex` and `sync.RWMutex` is a `sync.RWMutex` and `sync.RWMutex` is a `sync.RWMutex` and `sync.RWMutex` is a `sync.RWMutex` and `sync.RWMutex` is a `sync.",
      "reference": "I think we need to clear this out on logout, and update it on login, right?"
    },
    {
      "prediction": "I don't think this is a good idea, but I don't think it's a good idea.",
      "reference": "I think normally we'd make this a precondition (using e.g. `g_return_val_if_fail`), but meh, this works too!"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Is this header used by other outside service?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "that's fine by me to have simple test for provisioning check"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "These two methods seem to be identical except the names. Any idea why two methods are needed?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I don't see much difference between this and `create_db` module. How about having a function with a `database` argument?"
    },
    {
      "prediction": "I don't think this is a problem with the `getDataErrorComponent` method.",
      "reference": "See above, no need to pass the module name."
    },
    {
      "prediction": "I think this should be a list of (X, y) tuple pairs to use as a validation set.",
      "reference": "LightGBM supports multiple validation sets, so please leave `sets`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "you don't need to create a enum for this, java allows you to switch on a string ;) (since java 7?)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What is this obscure syntax anyway? o.O"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think we should have one for the CLA Classifier, and KNNClassifier as well. And how about RecordSensor?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do.",
      "reference": "Missing new line."
    },
    {
      "prediction": "I think this is a hack, but it's not necessary to use `options.strictPopulate` in the future, but it's not necessary to use `options.strictPopulate` in `options.strictPopulate` in `options.schema.base.options.strictPopulate` in `options.schema.base.options.strictPopulate` in `options.schema.base.options.strictPopulate` in `options.schema.base.options.strictPopulate`.",
      "reference": "`model.schema.base.options.strictPopulate != null`. Why hardcoding false? Also, `model.base.options` should work and be shorter. Finally, any way to move this up to the `populate()` function in `model.js` that calls `getModelsMapForPopulate()` and shallow clone the object before modifying? A bit random to modify this option here."
    },
    {
      "prediction": "Should we remove this?",
      "reference": "We now have Prepare.A/Build.A/Builders.Build.A - what are the differences?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Could you reduce this to one line and change the first argument to a single quoted backslash string? Perhaps we can add this as an option named `:preserve_backslash` to the manify method. That way, we don't need an extra method in the first two cases. Obviously, we still need it for the inline case."
    },
    {
      "prediction": "I think this should be an error, but it's not a problem.",
      "reference": "`has(default)` i think is the preferred way of doing this"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Does this mean we can only do rewrites if there are no `DeleteFile`'s?"
    },
    {
      "prediction": "I think this is the same as `make_contents(table=table_hash, file=file_hash)`, but it's the same as `make_contents(table=table_hash, file=file_hash)`.",
      "reference": "Actually, these are fine; we're using 110 as the max line length. (it's also set in the .pylintrc)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "No issue here, but what tool are you running to put these imports into the preferred organization? I have configuration to run `goimports` whenever I save a file, but it appears that that is not quite sufficient."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "guessing this method could/should close it but I didn't see where it was getting called."
    },
    {
      "prediction": "I think this should be a string, but it's not a string, but it's not a string, but it's a string, but it's not a string.",
      "reference": "Could you please use `camelCase` in the property name to follow the naming convention used in the rest of the properties?"
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "Can we revert this change? looks like an extra space was added at the end  "
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This just grabs any one of the proto services defined in the API, right? What happens when there are multiple (like with PubSub)?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Remove the pylint disable and remove the .format() from the string. The tablename is just 'violations'"
    },
    {
      "prediction": "I don't think this is the right thing to do with `exercise_ids` and `steps.where(exercise_id: exercise_id).update_all(position: index + 1)`.",
      "reference": "Will this implementation allow you to add new exercises to the trail?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Actually there is race condition here, because pointer assignment isn't atomic on some platform. But this is a rare case we should hit, we can just let it go for now. Maybe this is one of the TODO list."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We should check somewhere here and in the partitioned_io_buffer that the max_mini_batch_size is properly computed for each model and that it is not aggregate (sum) for all models. The global/max_mini_batch_size should be as specified by the user in the prototext/cmd line."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "you can change the string value, but not the code constant"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "File is not `goimports`-ed"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is this Todo necessary?"
    },
    {
      "prediction": "I don't think it's a string, but it's not a string, but it's not a string.",
      "reference": "I would recommend to leave out `None` because None is already the default."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I may have missed previous discussion on this; apologies if that's the case. What do you think about just `input-yaml`, without the `cli-`?"
    },
    {
      "prediction": "I don't think this is the right thing to do here, but I don't think this is the right thing to do.",
      "reference": "Nit: rename to sendError."
    },
    {
      "prediction": "I don't think this is a bug in Python 2.7.",
      "reference": "`pylint` wants to know why this `import` isn't at the top of the file; and it's kinda right"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "To me, using a `RuntimeException` for this feels a bit weird. I would just extend `Exception`, or maybe even `IoException`. Could you also please overwrite the `getMessage` function to return something like `\"Result does not specify a feed url\"`?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "what was the issue here? why did you have to directly set?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm confusied - Isn't `countryString` left empty if `len(country)` != 0?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Would you please update this by using `#if (QT_VERSION >= QT_VERSION_CHECK(5,15,0))` and `QSignalMapper::mappedInt` for Qt >= 5.15?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "This type of change opens a question on how we can cleanly shutdown or prevent all running agents so we do not run the risk of an agent holding kernel mountpoints, which can cause unsafe unmount/chroot exit. Will open a github issue to track this. This specific change itself is fine. It is a pointed change specifically for stopping the offending agent."
    },
    {
      "prediction": "I'm not sure why this is a class, but it's not a class.",
      "reference": "this file is model generated by protobuf, just for compatible test it's better not change it."
    },
    {
      "prediction": "I don't think why this is a hack, but I'm not sure if this is the case.",
      "reference": "It turns out we can send the reason as the property to Segment on the event. Then we can do whatever we want with it. In this case, I think we'll fire a web hook to Zapier which will add a note or message on the user in Intercom."
    },
    {
      "prediction": "I'm not sure if this is a method_missing?",
      "reference": "This class is very similar to `Catalog`. Is there a way to have this class compose a `Catalog` instance or extract a common class which they can both compose?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why did you decide to drop the `queue` from parameters of `wrap` function? The agreement was that all functions for DPC++ case that accept non-host-accessible memory shall accept the queue directly."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I think this is a bad name, as its not clear what it does by name alone. If we merge this it should be something like `use_links_to_files_in_output` and should take either a custom scheme like `rspec` or default to `file`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Arguably this is actually still valuable for perf, maybe it should just be a warning?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "didn't way say that the topology driver will actually insert the entries to the address book?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This seems safe to me. My guess is the original checks were a combination of before + after `oldParentVNode` became reliably a `(vnode | null)`."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea to use the `--filename-suffix` and `--filename-ext        ` option.",
      "reference": "also in the `.md` please."
    },
    {
      "prediction": "I think this is a bug in Rhel4, but it's a bug in Rhel4.",
      "reference": "RHEL is an acronym and is usually all caps. Why are you adding a redhat regex matcher?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Maybe I am daft but it looks like you removed fixed width readers but I don't see where you added any readers?"
    },
    {
      "prediction": "I don't think this is the default manifest type.",
      "reference": "@acud The reason I moved these here is because I need them in the traversal tests. The traversal package doesn't need this. I don't see any particular reason why any package apart from api would need this. api package imports traversal, so I cannot import api in traversal pkg. Also if these change in future, the traversal tests need to change. So maybe enough reason to move these here? That way both packages can access these as they both depend on manifest"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "I'd prefer this to be called `pinned` - also it should probably be in the `TabData` class instead, which is accessible as the `.data` attribute of the `BrowserTab` object - otherwise, `BrowserTab` would have a lot of quite \"random\" attributes :wink:"
    },
    {
      "prediction": "I don't think this is a bug in ChromeDriverCommand, but I don't think it's a bug in ChromeDriverCommand.",
      "reference": "Nit: `Headless` is one word, not two, and so doesn't need camelcasing in this way."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why not import audit as well?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `parent` property.",
      "reference": "OK, i think there will be more of those..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Can you add : 'password' => 'The provided password is incorrect.', ?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Extraneous blank line."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `axe.utils.getNodeFromTree(axe._tree[0], nodes[index]);` and `axe.utils.getNodeFromTree(axe._tree[0], nodes[index]);` and `axe.utils.getNodeFromTree(axe._tree[0], nodes[index]);` and `axe.utils.getNodeFromTree(nodes[index",
      "reference": "nitpick: use `const virtualTree`, I know it was `let` earlier."
    },
    {
      "prediction": "I don't think this is the right thing to do with the mdFlushListener.",
      "reference": "Actually, I think it might be easier to do it here. Rough outline: 1. Save a list of the md cache keys and new brmd while looping. 2. After the loop, for each entry: 2a. Look up the old cache entry. If it doesn't exist, continue. 2b. Otherwise, make a deep copy of it, and replace its brmd with the newly-generated one. 2c. Delete the old cache entry, put the new cache entry. What do you think? The problem with the current approach is that the gap between dropping the old version and putting the new version is large enough that when we put the new version, we may be kicking out hotter cache entries. In this case, we'd be doing so to a lesser extent. Ideally, we'd be able to replace the entry in the MDCache LRU without changing the LRU info."
    },
    {
      "prediction": "I'm not sure if this is a rooted path?",
      "reference": "We need tests for this"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "NewExporter takes in two arguments: a configuration for the metrics connection and one for the traces"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why not use currentPlayer instead of playbackManager.getCurrentPlayer()?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the params.require(:user).permit(I don't know how to do this?), but I don't know how to do this?",
      "reference": "Avoid comma after the last parameter of a method call, unless each item is on its own line."
    },
    {
      "prediction": "This is a hack.",
      "reference": "You should remove the outdated sentence."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Please restore the empty line after the group of `STATE_*` constants. This visual separation makes the code easier to read."
    },
    {
      "prediction": "I think this.core.on('core:complete', (successful) => { this.core.log(`[GoldenRetriever] removed ${fileIDs.length} files that finished uploading`)",
      "reference": "Unsure why this is `RestoreFiles` now vs `GoldenRetriever`, thought we deprecated the first?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Not sure what this is. Bad merge?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I'm confused, what did this actually fix? Is there a reason we are setting `err` in the parent scope to `nil` in this round-about way?"
    },
    {
      "prediction": "Should we add a test for platform?",
      "reference": "Can we remove this   ?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I think this is a bug in the tests.",
      "reference": "line is 195 characters (from `lll`)"
    },
    {
      "prediction": "I don't think this is a bug in the future.",
      "reference": "could not import k8s.io/kubernetes/pkg/util/slice (invalid package name: \"\") (from `typecheck`)"
    },
    {
      "prediction": "I think this should be a function, but it's not a function.",
      "reference": "@disordinary would you be able to configure your editor to use the `.editorconfig` file so that we can avoid final newline changes?"
    },
    {
      "prediction": "I'm not sure if this is a collection.",
      "reference": "I really think we should not use this style where unused arguments are named with underscore. While this eases the person writing the function it does it at an expense of readability and debugging. So next person who needs to actually use this argument will need to check the spec and rename this to `obj` and then use it or if he is debugging it he will is not able to watch for a meaningful variable name and will need to inspect `_` which is weird and uncomfortable. We have not used this style anywhere in the code while I agree its very tempting to use it :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Thanks for avoiding the default value for the param. But, I think sending heap as NULL might make this program to fail. Have you tested this program? If you have tested this program already, then this PR is ready to be merged."
    },
    {
      "prediction": "I'm not sure if this file is in the project root.",
      "reference": "Don't make it sealed"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Did we miss that for jwt before?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "It appears that using SERCOM1 was a bug: the only SERCOM that is supported on the TX/RX pins is SERCOM0. Previous UART support wouldn't have worked on the Trinket M0 TX/RX pins anyway (`PA06`/`PA07`). This PR fixes that, and should thereby add support for UART on the Trinket M0."
    },
    {
      "prediction": "I don't think this is the default locale, but it's not the default locale.",
      "reference": "Spaces for indentation, not tabs"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "doing this as a binding map was insane, but with the ConstBindingIterator to hide the binding->index gunk and avoid the hashes during access it sticks out."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "nitpick: I'd rather move this into the test method directly (we should avoid variables at the root scope if they are not reused in multiple places). (not critical, though - shouldn't hold back the merge..)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "You should do: AssertEx.AreEqual(importPeptideSearchDlg.CurrentPage, ImportPeptideSearchDlg.Pages.match_modifications_page);"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "SC support batch register schemas we should swtich to new api be careful that maybe will send too big request, need to split to multi request by max size of limit."
    },
    {
      "prediction": "I don't think it's a bug in the Go compiler.",
      "reference": "At this point, maybe it would make more sense to write this as a range rather than listing specific versions?"
    },
    {
      "prediction": "I think this is a bug in proxy_test.go, but it's a bug in proxy_test.go, but it's a bug in proxy_test.go, but it's a bug in proxy_test.go, but it's a bug in proxy_test.go.",
      "reference": "I guess we can start by putting the `const StatusContextCancelled = 499` at the bottom of this file"
    },
    {
      "prediction": "I think this is a bug in the tests.",
      "reference": "Blocking: populate a non-empty value and check it below."
    },
    {
      "prediction": "I don't think this is the right thing to do.",
      "reference": "What is this number value for? How is it used?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "This needs an end keyword"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think this is the first record type in Datadog.Trace!  "
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `onCompleted` parameter.",
      "reference": "Nit: missing newline above."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since it's a one-off, worth putting an info log before and after."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'm sorry, but the indentation is still wrong. This should be indented by one tab."
    },
    {
      "prediction": "This is a hack.",
      "reference": "can we add an example?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "We usually avoid blank lines at the start of functions."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I dont think this line is needed"
    },
    {
      "prediction": "I think this is not a valid value for the feature gate?",
      "reference": "We should not panic here !!! We return error i.e. 500 http code"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "To avoid useless calls to `conf.l2types.get()` we could have a `set()` of types that are OK in this PCAP files. We could check if `p.__class__ not in self.l2_types_seen` first, only run this code block in that case, and add `self.l2_types_seen.add(p.__class__)`. I'm not sure if I'm clear here... let me know what you think."
    },
    {
      "prediction": "I don't think this is the default value for the source, but it's the default value for the source.",
      "reference": "Shouldn't \"source\" be a noun? How about? -EXECUTION_SOURCE_USER -EXECUTION_SOURCE_SCHEDULE -EXECUTION_SOURCE_EVENT (because it's an event based trigger mechanism)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Should not switch to `lvis_v1_instance` here because that base config uses ClassBalancedDataset to oversample the data."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `th-has-data-cells` attribute.",
      "reference": "Last time I checked, this technique did not work on all major screen reader - browser combinations. What screen readers have you tested?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Most tracer settings can be set in several ways: environment variables, `app.config`/`web.config` file, or in a json file (`~/datadog.json` by default). Most exceptions to this rule are settings in native code (where we use env vars only). Currently, `DD_TRACE_ASPNET_ROUTE_TEMPLATE_RESOURCE_NAMES_ENABLED` will only work as an env var. Was this limitation intentional?"
    },
    {
      "prediction": "I think this is a bug in the ECS agent, but it is not possible to register the instance with the same identity document.",
      "reference": "Would \"DisableIID\" be a better name? For example, we used DisableMetrics, ImageCleanupDisabled, ... etc. for other similar fields."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "So this is a swing of 2: but I think we only need to reduce by 1? The artificial jump added on truncation is not passed to clients: it's like other mangling added later. So if `-max_bb_instrs 4` means 4 app instrs passed to clients, we'd want ==, not ==-1, right? Plus, if we did want -1 and to stop at 3 instead of 4, this is not sufficient: the inner loop above currently has `total_instrs <= cur_max_bb_instrs`."
    },
    {
      "prediction": "I'm not sure if this is the right thing to be converted to C strings, but I'm not sure if this is the right thing to be converted to C strings.",
      "reference": "Does Tinyint belong to this set of types? I suppose the answer is No, but thought it safer to check."
    },
    {
      "prediction": "I think this is the right of the workspace, but it's not the right of the workspace.",
      "reference": "I'm a bit leery of this implementation, because it assumes that the only \"outside\" is to the right side. Note that Blockly assumes that there's nothing useful to the \"outside\" of the toolbox, based on the configuration of the workspace, so it's not like we're doing the right thing either. I think this will break in RTL. If you keep the editor in the same place but inject with RTL, everything you're looking for will be in the delete area. If the editor and stage swap places, this will just be looking on the wrong side."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Just spotted the `local` on here; that shouldn't be needed - no reason to limit this config to env vars only"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "That's a tricky one, as the variable is indeed used in line 2346, which is a `logInfo` message that is not compiled unless `INTERNAL_DEBUG` is set or `CMAKE_BUILD_TYPE` is set to `Debug`. Our CI builds with `INTERNAL_DEBUG` to verify that all `logInfo` are correct, and thus we don't get the warning. The best is probably to remove the iterator (as you did), as well as the part of the log that uses it."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I suspect L2Socket needs a similar change (line 502) for the case where `iface` is None (line 479)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do. I'm not sure if this is the right thing to do.",
      "reference": "Was this all that was needed to add CRUD operations for the LicensePermission model? :-)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Did you look for other locations that compare name? I expected there to be more."
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "There were some requests internally to allow users to opt out of this behaviour. We could expose a property that allows people to toggle ti"
    },
    {
      "prediction": "I think this should be a test case.",
      "reference": "Nice -- this forced `merge-on-getReader/commit` to be used more often in this test?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Instead of a `bool`, can we just call this `MaxAssetDecimals` and have it be a `uint8`/`uint16`/`uint32` whose value is 0 before the upgrade and 19 after (2**64 - 1 is 20 decimal digits)? We'll need to set a maximum value anyway, and that way there's only one new proto variable instead of two."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "where `$aliases` is defined ? @javiereguiluz"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "what is the justification for the removal of the registered label? it doesn't seem to have high cardinality nor is it redundant. Seems useful to shed insight into understand situations where workloads aren't registered...."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "`ctx` is unused in ListEvents"
    },
    {
      "prediction": "I think this should be a test for the sqlcipher version.",
      "reference": "We've had that test on iOS for years."
    },
    {
      "prediction": "I think this is a bug in Roslyn.",
      "reference": "This is for creating binlog file for building bdn generated template project. I feel that it's may be helpful in general for bdn diagnostic purpose."
    },
    {
      "prediction": "I don't think this is the right thing to do with the `new_tab` and `new_window` arguments.",
      "reference": "Can you adjust `open_path` to simply call `path_to_url` and then `open_url` instead of duplicating the code?"
    },
    {
      "prediction": "I'm not sure if this is the case for a single request.",
      "reference": "I'm curious -- do we have information on the upper bound of the delay we would expect with high probability from a peer with no network issues? My intuition is that we want to set this as low as we can reasonably get away with before we start killing productive connections. My uninformed intuition is also that 10 seconds is probably higher than we need and I'd love to know if this is wrong and 10 seconds is already pushing the limit."
    },
    {
      "prediction": "I think this should be the case of a negative number?",
      "reference": "what happens if it's == 0"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "We could potentially log a message here instead that indicates the transport does not support `run-as` on Windows and will be ignored, just in case users expect it to and are surprised. Since it would _always_ be logged when using `--run-as` on Windows, even when the transport isn't being used, it would probably want to be either at debug or trace level."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Did we need this alias? Or is it just a holdout from development?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This should have failed before."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Slower construction, faster matching. I wonder if this will be noticeable in the relenv?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I think that if `data_discovery_count_ > static_cast<int>(throughput_publisher_.subscribers_)`, then we should not proceed, since we have discovered some unexpected subscriber that can affect the test results. I'd change the comparison to `==` and have and `else if` contemplating the `>` case"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Remove that include"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `options['view']` or `options['entity']`?",
      "reference": "IMO this should be defined in the form theme instead. This class should always be there. If the user configured additional css classes, it should be appended instead of replacing the `{view}-form` css class."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "These tests actually go to the server."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This test modification isn't correct. This task could run immediately and you wouldn't be able to tell if OnCompleted was called or not."
    },
    {
      "prediction": "I don't think this is the case for `component.componentWillReceiveProps` and `component.componentWillMount`?",
      "reference": "I'd be open to loosening this check if it can help offset the size."
    },
    {
      "prediction": "This is a hack.",
      "reference": "I'm wondering which we should use, stable or latest?"
    },
    {
      "prediction": "I think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "possibly extending EncodingType enum?"
    },
    {
      "prediction": "I don't think this should be the case.",
      "reference": "I tested it only in Firefox (`./go //rb:firefox-test`)"
    },
    {
      "prediction": "I think this is a hack, but I don't know how to do this?",
      "reference": "can we do this in the baseexporter itself? So that exporters just access this.Provider.Resource, and baseexporters take care of populating Provider?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `countly.models.js` and `countly.views.js` and `countly.events.models.js` and `countly.events.views.js`",
      "reference": "what is the difference between `/core/events/javascripts/countly.views.js` and `/core/events/javascripts/countly.events.views.js`"
    },
    {
      "prediction": "I don't think this is a bug in axe.a11yCheck.",
      "reference": "We should make sure this is also supported by `axe.run`. Perhaps moving it into run-rules would cover both API methods more easily?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If the `MemoryBasedStorage` relies on a `self._bump_and_store_timestamp()`, then every child class will have to implement it. So it should not be prefixed with `_`. And should raise `NotImplementedError` etc. :)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why removed the MemoryDiagnoser attribute?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why do this instead of `localFieldPath.applyGetters(doc[localField], doc)` ?"
    },
    {
      "prediction": "I'm not sure if this is a semantic match, but it's not a semantic match.",
      "reference": "Just for a check. Do you really want to delete this?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "github.com/golang/protobuf/proto group in next group"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Nit: what about just `pay`? Is there some other subcommand that would conflict with?"
    },
    {
      "prediction": "I'm not sure if it's a string, but it's not a string.",
      "reference": "Just for the sake of keeping things logically co-located, I'd like to see this functionality in `Quantity.java` which has a lot of utility methods related to this. Maybe a `static` method like `Quantity.isValid(String string)`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "How about use `protected` ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should it not be `common.HashLength*2 + common.IncarnationLength` ?"
    },
    {
      "prediction": "I don't think this is the case where the job was killed by the SLA.",
      "reference": "those change are done by save plugin."
    },
    {
      "prediction": "I'm not sure if this is a string, but it's not a string.",
      "reference": "There were problems with NullPointerException and with german Umlauts in message titles (I know they're not allowed in the specifiation but they caused my K-9-Inbox to not work at all) I don't know if this is related to PGP/Mime"
    },
    {
      "prediction": "I think this is a bug in Datadog, Inc.",
      "reference": "This is an appsec concept right? Should it live in the Appsec namespace?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "I'd personally recommend having the demo check for error, unless it's worthless."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Since this is in a test, I imagine that the choice of `info` level was deliberate."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `findAllDOMElements` function?",
      "reference": "good call swapping these names! makes more sense this way i think"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe leaving this out will save some bytes as in let `let isHydrating = replaceNode === null`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Let's manually create one extra whitespace line here (code_ += \"\")"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "nit: copy or clone"
    },
    {
      "prediction": "I don't think this is the case for a map or a struct.",
      "reference": "I think this can be called `HasField`, because that's what it's doing. It really is independent of revision."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Is this to avoid collisions?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "nit: a better name for this variable would be enableLogStats, but it's beyond the scope of your change."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Because linters don't handle reports now, this was breaking the setup for _all_ tests. I deleted it so I could run my tests, but I didn't check the impact on other tests as many tests are failing at the moment."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "I'm not really a fan of this -- why not set up logging for `init` here (or setting a global flag) rather than doing it this way?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is my favorite part of this PR. Being able to `import` 3rd party tools will hugely improve our workflows. :heart:"
    },
    {
      "prediction": "I think this is a bug in the source forge.net.",
      "reference": "having this extend `UnsynchronizedStaticFormatterRule` seems semantically incorrect even if it works  we should probably refactor `UnsynchronizedStaticFormatterRule` into a `UnsynchronizedStaticAccessRule` which can be configured through properties to track unsynchronized static access to any given types (with proper defaults to include `Formatter` and `MessageDigest`). This will also scale better as new types are suggested to have a thread-safe access enforced. The `UnsynchronizedStaticFormatterRule` can be marked as deprecated at the ruleset level, point to the new implementation, overriding the property defaults to keep just looking for `Formatter`. Moreover, the `THREAD_SAFE_FORMATTER` static should probably be replaced with a property of thread-safe classes to ignore, once again with proper defaults."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Keccak.Zero should not be used to mean null"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "perhaps add a couple more edge cases."
    },
    {
      "prediction": "I don't think it's a bit_flag, but it's a bit_flag, but it's not a bit_flag.",
      "reference": "Is this blank line needed, or typo?"
    },
    {
      "prediction": "I think this should be an error.",
      "reference": "This was a major PitA to find: it was causing some huge goroutine leaks and unfinished prefetches."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `instance_methods.map` method.",
      "reference": "you can use Enum#flat_map here."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Same potential FP: The stream is provided from outside (here as a method parameter), so we should not be responsible here to close it, should we?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Put a comma after the last parameter of a multiline method call."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "It seems like this is the only way to access javascript `static` methods from Java."
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why was this removed here?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "i am aware that you did not add these, but might i ask why we need these one-liner funcs instead of just exporting the struct fields in the first place?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I agree with this because it is the opposite of `GetProjectedIds` used above."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "add 'sriovNetSupport' also to this list"
    },
    {
      "prediction": "I don't know why this is the case. I'm not sure if this is the case.",
      "reference": "Code style issue: `if` body is not wrapped in braces."
    },
    {
      "prediction": "I don't know why this is the right thing to do?",
      "reference": "Call requires API level 11 (we are on 10)"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "do we need to pass the DB if it is the same"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "Might be a good idea to rename the variable so it doesn't shadow the type."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Again I'd prefer if this is done in JavaScript rather than in SQL."
    },
    {
      "prediction": "This is a hack.",
      "reference": "there is still `2` spaces after `a` here.. :P"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What we did in docker before, when working directly with libcontainer, is check if the source is `/dev` and the destination has a `/dev/` prefix. This implementation is probably ok. If someone is mounting their own `/dev` I would expect it to be pre-configured and not need the extra check for if it's the host's `/dev`. (that said, I've not tested yet, just reading through the code)"
    },
    {
      "prediction": "I don't think this is the case for the `FF_JAVA_SELF_EXEC` flag, but it's not the case for the `FF_JAVA_SELF_EXEC` flag, but it's not the case for the `FF_JAVA_SELF_EXEC` flag.",
      "reference": "you should add some help on the struct too so that `plz halp featureflags` has a bit of explanation. Might be worth mentioning that these generally won't remain around very long relative to other config options (i.e. they're typically enabling \"preview\" features for the next major)."
    },
    {
      "prediction": "I don't think this is a problem with the `ExperimentPayments` flag.",
      "reference": "Maybe `consumerID, receiverID, issuerID`, at least it's a convension in overal repo"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `s3.S3` protocol.",
      "reference": "Where does the auth go?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "0 < minimum gas price, `ErrUnderpriced` is more proper"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "these should be alphabetized"
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack.",
      "reference": "These changes look concerning. It looks like the old offset (only index) must not have been correct. If so, there are places where `getDataBuffer().setLong(...)` and similar methods are called but aren't updated like these. Are those cases bugs as well?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "the CAS call here is now wrong since dirty will never be 3 anymore. it might be useful to sweep through the entire usage of this field to see that everything is correct"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Base model is imported here"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "import but not used"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "What about the call in `case PACKED` just below? Does that also need to use the `typeWidth`?"
    },
    {
      "prediction": "I don't think this is a bit of a hack, but it's a bit of a hack, but it's a bit of a hack.",
      "reference": "not sure i like this change. The encryption package does not need to know about references"
    },
    {
      "prediction": "I'm not sure if it's a bionic bionic llvm-7 package.",
      "reference": "This shouldn't be added. It's not supported. It's not event the default. If we are going to support this, we need to have CI for it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "omg only four left!!!!"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "I'm not really sure how this would happen. once the binary is already compiled, the config.Consensus should already have the entry for protocol.ConsensusCurrentVersion."
    },
    {
      "prediction": "I don't think this is a test case, but it's not a test case.",
      "reference": "Is there a reason for the order swap here?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Where will this exception get caught ?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why this field is made public?"
    },
    {
      "prediction": "I think this is a hack, but I think it's not a good idea.",
      "reference": "Is the `vmultiplier` only used here for checking if a grid value is nodata?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Is this deliberate? If so, why?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "both URL works. I corrected it anyway."
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Rather than have another member and and if/else statement, if the user passes in `PreInvocationAuthorizationAdvice` it could be adapted to match `PreInvocationAuthorizationReactiveAdvice`"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "The callback get the log level as a number."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "Is there any issue with 2.2.3? If not this should be `<2.3`.  "
    },
    {
      "prediction": "I think this is a bug in the SQLTestCase.",
      "reference": "Shall we keep this test?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the form engine.",
      "reference": "When would this be the case? / When would SelectElement not be available? Is this change compatible with 6.2? (I'd like to roll a release that works with 6.2+ first, before moving on to 7.x)"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "how about rename to shouldNarrowDataTypeTo?"
    },
    {
      "prediction": "I don't think this is a hack, but I think it's a hack, but I don't think it's a hack, but I don't think it's a hack.",
      "reference": "Why not check that the one available renderer is 'bokeh'?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Can you import `bundler.ErrOverflow` rather than redefine it here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is just a renaming of the function getResourceType() to getResourceReference()"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Seems like this might need to allow for `\"`s to be used here?"
    },
    {
      "prediction": "I don't think this is the right thing to do with `g_luaEnvironment.getCombatObject(g_luaEnvironment.lastCombatId)` and `g_luaEnvironment.getCombatObject(g_luaEnvironment.lastCombatId)` and `g_luaEnvironment.getCombatObject(g_luaEnvironment.lastCombatId)` and `g_luaEnvironment.getCombatObject(g_",
      "reference": "here you assigning it to a local variable, in the original code it assigned to combat(CombatSpell member). Not sure if CombatSpell needs to use a shared_ptr since currently it does not and it works \"good\"."
    },
    {
      "prediction": "I'm not sure if you're happy, but I'm not happy.",
      "reference": "Should we also remove this? This applies to subscriptions in general, but it seems sort of weird in the context of products now."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "I think we should keep these, o.w. our examples will be wrong (where we're importing from `dagster.utils`). Also, we might break folks who've imported following our docs."
    },
    {
      "prediction": "This is a hack.",
      "reference": "This is good and something that I think opens a lot of possibilities. I think what would be even better is to change up `TracerProviderSdk` to take factories for the processors just like it already does for the instrumentations. Should probably use use a factory for the sampler. If we made those 2 changes then we could actually split this all up into the config and the build phase and we could use the factory methods in the hosting version to call into the IServiceProvider to get those instances."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "Is there a way to make it so `values.New(nil)` works instead of adding a new function?"
    },
    {
      "prediction": "I'm not sure if this is the case for Symfony 2.8, but it's not the case for Symfony 2.8.",
      "reference": "> when requirement of Symfony **will be** >= 2.8 Same for others."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'd like to see if this can just be set on the service account instead of the project. Using the SVC_ACCT_ROLES (which should otherwise be deleted as I don't think anything else is using it.)"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Please remove the unused imports :)"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Were these local edits? There doesn't appear to be a change here. If so, let's remove this from the commit."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: this should be further down w/ the rest of the github imports"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I don't know if this is something we should address now, but we have a cents_to_dollars private method in both `SubscriptionCoupon` and `Invoice`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Formatting here and all below: missing space before open bracket for the compound statement."
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Avoid using old mortbay utilities for converting JSON. Uses existing Solr Utils to convert from JSON string."
    },
    {
      "prediction": "I'm not sure if this is a `CommandOperationV2` object, but it's not a `CommandOperationV2` object, but it's not a `CommandOperationV2` object, but it's not a `CommandOperationV2` object.",
      "reference": "I actually think this wrapping is great, but let's call it `RunCommandOperation`?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Maybe it is better to add checking for status code duplications? It can prevent some stupid copy-paste user errors."
    },
    {
      "prediction": "I don't think this should be the case.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "This lea should match instr_check_xsp_mangling and be undone. I don't think i#3307 applies here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I like the idea of this being an interface as it makes the test setup a bit easier, thoughts?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Nit: I believe the electrum convention is to use `bfh` instead of `bytes.fromhex`. Great catch on this bug!"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Use a more granular error type. I would recommend `ValueError` in this case."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "A space after each argument, and an empty line above this if-statement."
    },
    {
      "prediction": "I think this is a `memo` function, but it's not a `memo` function, but it's not a `memo` function, but it's not a `memo` function, so it's a `memo` function.",
      "reference": "Things like this make me wonder whether we should ship a \"development\" and a \"production\" version. I remember the discussions about making things more complex bundling wise but couldn't we omit this line in a \"production\" or \"minimal\" variant of our build? That would save us some bytes here and there. Or are we somehow able to move this line to debug? I though about monkey patching the exported function but that only works in CJS and not ESM AFAIK."
    },
    {
      "prediction": "I don't think this should be used.",
      "reference": "Maybe rename to `RegisterListener` or `RegisterSubscriber`?"
    },
    {
      "prediction": "I don't think it's a `null` here, but it's a `undefined` here.",
      "reference": "My one concern here is that we are adding a new array allocation for each depth of the tree which could add some non-trivial GC churn. Perhaps this would be okay if we think that refs are used through a tree commonly enough such that they'll get allocated anyway but I'm not sure refs are *that* often used. Every app has a couple, but probably not at every level of their app :/ So maybe the extra bytes are worth it in this case? Though I have no data to back up my hypothesis so I could way off lol."
    },
    {
      "prediction": "I don't think this should be the case.",
      "reference": "We should get rid of this big array and think about a better way to check this."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Should we cache the result of `Mvx.Resolve<IMvxChildViewModelCache>()` to avoid a lookup each time?"
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "If you get to this line avg_size_of_message is an undefined value, yet you use it below. You you should set this value to something in the exception block."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "let's just fold this inline in mux.go, no need for the indirection to this new file"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "This bit confused me just now as I was reading through -- turns out this is due to the `{@link}` on line 316. Reading up on this, the alternative seems to be to state the fully qualified name instead. Happy to edit if requested as I don't have a strong view either way (perhaps a small leaning towards keeping the import)."
    },
    {
      "prediction": "I think this should be a test, but it's not a test.",
      "reference": "There's a unnecessary System.out."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Should we add the flows only when NodePort is enabled?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "ITYM to flip this one..."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "What's the difference between typescript-eslint/eslint-recommended and typescript-eslint/recommended? I really can't get it."
    },
    {
      "prediction": "This is a hack, but it's not a good idea, but it's not a good idea.",
      "reference": "Thinking: Maybe it would be more useful to define this in terms of RTTs. That would also make it easier to switch this to a bool, since we could then pick a reasonable default value. Unless of course an attacker could influence our RTT estimate. Is that the case?"
    },
    {
      "prediction": "This file is part of the code.",
      "reference": "Why is this line deleted?"
    },
    {
      "prediction": "I think this should be the case when the node finished initial boostrap is called.",
      "reference": "minor type `boostrap`"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Nit: please don't separate imports into groups."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Thinking if it would be nice to have something like `setNothingSelected`."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think this is a useful InfoLevel message. In production, if webhook client connections suddenly start failing due to change of serving cert, you'd want to see this information in the logs."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Generally, if cast from int to char*, you could cast directly. Because no errors should happen."
    },
    {
      "prediction": "I don't know how to do this?",
      "reference": "Is 10 min too long? What do you think about 1 minute? Unless there are many jobs in this state, I don't expect the CPU overhead to be too high."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can you remind me why we keep the pointer if it's a `map[string]<PStruct>`? are there other scenarios where the pointer is kept?"
    },
    {
      "prediction": "I'm not sure if this is a single instance of RewriteDataFilesAction.",
      "reference": "Would it make sense to also add `setMaxParallelism` in addition to this to match the Flink API?"
    },
    {
      "prediction": "I'm not sure why this is a `ModalComponent`?",
      "reference": "Not needed for actions. `_super(...arguments)` is only needed when you're extending from a base class and want to run the logic in the base class before your own logic"
    },
    {
      "prediction": "I think this is a hack, but it would be better to use `_hydrating: true` instead of `_hydrating: true` instead of `_hydrating: true`",
      "reference": "I still need to run this code to verify my understanding, but my first reading through makes me think this may need to be `suspendingComponent._vnode` since we set `vnode._hydrating` on the vnode that threw the error (diff/index.js:275), not on `Suspense._vnode` (though we could in Suspense's `_catchError` implementation at the top of this file)."
    },
    {
      "prediction": "I don't think it's a local file, but it's not a local file, but it's not a local file.",
      "reference": "I think it's a good idea to log this as debug, the same way the other branch gets logged."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "1:D100: Docstring missing 35:D101: Docstring missing 37:D102: Docstring missing 42:D101: Docstring missing 44:D102: Docstring missing 57:D102: Docstring missing 66:D101: Docstring missing 69:D102: Docstring missing"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "keeping this as an unexported constant, as importing the role pkg creates a cyclic dependency."
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Why `c.RevisionField()` here but `c.opts.RevisionField` just below?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: this file diff seems unrelated and probably should have been a separate PR"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "@sjplimp just checked this API in the latte repository master branch (which is what Install.py downloads) and this still does not provide the 18th argument. We cannot merge this pull request until this is available. i would also suggest to implement a second binding, a function called latte_abiversion() returning an int with an ABI version number (starting with 1). This way, it can be tested, whether the ABI expected by the LAMMPS interface and provided by the library is compatible *before* calling the `latte()` function and risking a segmentation fault."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Is this from debugging?"
    },
    {
      "prediction": "I think this should be a mock object, not a mock object.",
      "reference": "Its betet use MockedObject"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "\"including\"? Since it doesn't take any parameters, I'm not sure how it can update anything else..."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "nit: I'm assuming you have verified this is what the error message should read like"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why do you need that? (real question)"
    },
    {
      "prediction": "I think this is a bug in CppTemplateParameterList, but it's a bug in CppTemplateParameterList.",
      "reference": "If I understand the patch correctly the `else` is no longer required."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Properly describe valid flag values here: `neither` should be replaced with `none` as they parsed below."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we escalate this to `warn`. It is a major event."
    },
    {
      "prediction": "I don't think this should be changed.",
      "reference": "Please move these up to line 86 so the numbers are in order."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "Add a docstring to contain the paper link."
    },
    {
      "prediction": "I think this is a bug in the compiler.",
      "reference": "Instead of adding the `--target` flag here, the `Target` struct should be set up correctly. Assuming this is for the Raspberry Pi 3, adding it to the `cflags` key of the JSON file should be enough (if not, you can print `config.CFlags()` here to check whether `--target` is already included)."
    },
    {
      "prediction": "I think this is a bug in the server.",
      "reference": "The changes in this file look unnecessary since `rpccontext.AuditRPCWithTypesStatus()` already does this check. Was there a reason you needed to add them?"
    },
    {
      "prediction": "I think this is a bug in the source code.",
      "reference": "you could probably use `const` for both?"
    },
    {
      "prediction": "I'm not sure if this is the case for `axe` and `axe.isFocusable` in `axe.isFocusable` in `axe.isFocusable` and `axe.isFocusable` in `axe.isFocusable` in `axe.isFocusable` and `axe.isFocusable` in `axe.isFocusable` in `axe.isFocusable`",
      "reference": "This looks like an \"ES Module\" to me. I do not understand this TODO."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Iceberg doesn't use `final` because it is unlikely that this actually helps. In Java 8, final detection is quite good, which is why non-final variables can be used in closures and lambdas. And final doesn't produce different byte code so it can't do much to help at runtime."
    },
    {
      "prediction": "I don't know what to do with the `getIP` method?",
      "reference": "There's `pushString` to use with C++ strings."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "qq: Should this include the iptables6-save sim. to the inverse checks above?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What about async user writers? We could be checking `param.mode == ASYNCHRONOUS_WRITER`"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the lombok.NoArgsConstructor annotation?",
      "reference": "this double check for lombok annotation + specific lombok annotation seems pointless, just keep the second (specific) check. Moreover, since we have a property with ignored annotations... why don't we use it? a user may setup the property and it will be ignored here. Also, this class should probably not extend `AbstractLombokAwareRule` anymore. We have a configurable set of annotations that suppress the warning, defaulting to ALL lombok annotations, yet we only check for `lombok.NoArgsConstructor`... Maybe directly extending `AbstractIgnoredAnnotRule` and settig the default property to `lombok.NoArgsConstructor`? Or, to avoid a breaking API change, keep extending it, but override the default. For 7.0.0 we can change the class hierarchy."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: the ordering may be misunderstood, as \"invoked in the same order\" could suggest the passed-in functions are called in-order, but the actual wrapping is LIFO. Some other ways to describe it (don't think any of these are ideal, but maybe it will help you come up with something better), * the handled returned by the first interceptor is executed first * interceptors are applied outside-in (don't like the terms outside/in though) * interceptors are applied in LIFO order, leading to an earlier interceptor's handler being executed before latter interceptor handlers"
    },
    {
      "prediction": "I don't think this is needed.",
      "reference": "We should not use a static import to be consistent with other existing use of the QueryElevationParams."
    },
    {
      "prediction": "I don't think this is a bit of a bitstream.",
      "reference": "No need to check return value?"
    },
    {
      "prediction": "I don't think this is a bug in PyQt5.",
      "reference": "~~Feel free to ignore that one, I'll fix things up when regenerating the `requirements.txt`.~~ As for the one below, this smells like a pylint bug..."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "it's a bit strange that this doesn't match `aggregationElements` which is what I would expect. I guess I am not familiar enough with go-ipfix."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Same thing: `num_simd_registers`. Ditto below."
    },
    {
      "prediction": "How to do this?",
      "reference": "Should be 2.1.1"
    },
    {
      "prediction": "I don't think why this is needed?",
      "reference": "nitpick: `required_subject` doesn't seem to be used here"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "We can revert this to reduce the diff of the PR."
    },
    {
      "prediction": "I don't think this is the right thing to do with the UIAElement.cachedIsContentElement and self.UIAElement.cachedIsControlElement",
      "reference": "Extraneous blank line."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Is this the same import as in the line 20?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "why those additional checks after published? template.version should always be present and greater than zero"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "I did not see this is used in the controlplane API? Is it for internal use only? Then no need to define it here?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we also add a line to print gcnArch?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I merged already so need another PR, but I think this needs to be at the bottom."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "space in key string?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The commends of this function should be updated"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The docstring is outdated."
    },
    {
      "prediction": "I think this is a bug in Datadog.Trace.",
      "reference": "Could rename to `ServiceVersionKey` for consistency with the suggestion to rename the TracerSetting."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case.",
      "reference": "I seem to recall a UI issue with this... @akarve I think you didn't like this for some reason..."
    },
    {
      "prediction": "I'm not sure why this is the default setting?",
      "reference": "The `MediaBlockService` commit must be remove"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "Use a literal constant here, and use `assertEqual`, e.g. `self.assertEqual(2, len(...))` You should also check that the number of rules is correct, i.e. 1 rule for buckets, 0 rules for tables."
    },
    {
      "prediction": "I'm not sure if this is the case for Uppy v3.",
      "reference": "@Murderlon Should it just say `some future version`?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "change looks good.. but, better to make populateVersion to return same object in the case of error.. that avoids lot of complex logic and probable issues"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "invalid operation: exp (variable of type *Service) has no field or method getAddressDetails (from `typecheck`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Probably overkill, but maybe we should be using a fake clock here. I won't push on whatever you decide though."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "If you feel like it, may as well apply all the suggestions below to this test too."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "do we really need a relation or can we just assume INTERSECTS?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Is this a `MetricKey` ?"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "what's your rationale to pick up this date?"
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "NIT: I'd have preferred that the new package be called \"utils\", but that's not a big deal."
    },
    {
      "prediction": "I think this is the default encryption state for an Amazon S3 bucket.",
      "reference": "Simple Storage **Service**"
    },
    {
      "prediction": "I think this is a better way to do this.",
      "reference": "I think, retrieving the setting could also be done outside the loop. What do you think?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This TODO isn't related to this change. We should remove it."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We chose `info` in the test code for obvious reasons. Changing to `finest` makes debugging harder and noisier."
    },
    {
      "prediction": "I think this is a bug in Python 3.2.",
      "reference": "I'm not really sure this is worth it. Keep in mind that every special case we add has the potential to introduce new errors and complicates the code further. For common cases that is acceptable, but in this instance I don't think it's beneficial."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "nit: this `if` isn't necessary since we immediately follow it up with a range over the slice, which works fine with a `nil` slice."
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "Remove this line please."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why is this is class field? it should be something local within the auto apply template method since we only need this once to process templates and never use again."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I agree with Stephen it's better to invoke getStandards() only once."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `irregular_dims` argument.",
      "reference": "After discussing what ``irregular_dims`` really is, we agreed that we need a better name that makes it clearer that this is more of an xarray concept of irregular dimensions than a holoviews one."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "This code is new and not tested well. While we may drop the log level before we ship 4.0, right now this is extremely helpful to users."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "this makes sure there is some padding space around the size column"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Put these includes in alphabetical order"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can this just be an else?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Merge this line with Line7"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do, but I'm not sure if this is the right thing to do.",
      "reference": "`clearfix` is needed to stop the `float:right` content overflowing the list item container."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "Can this be put on the assembly?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Could we rename the parameter to `overrideStatusCode`? The name `alwaysOk` implies that the health check result would be always healthy.  "
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "\"/schedpolicy\" is repeated, i would make it a constant and use it here and cluster client.go"
    },
    {
      "prediction": "I don't think this is a problem with RSpec::Core::Ordering.",
      "reference": "Having a second `configuration` arg seems kinda odd to me as an interface. It looks like you're just using it as a form of dependency injection for the tests, right? Part of what makes it seem weird is that it's leaked into all the other orderers where they don't use `configuration` at all. Instead, what do you think about accepting the configuration in `initialize` (and having it default to `RSpec.configuration` in the same way)? To me, the config feels like a bit of state the instance should hold onto rather than being given each time `order` is called. It also means the other orderers wouldn't need to take the odd second argument. Thoughts?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "This button should also be disabled when in secure mode since it opens a web browser from which you can easily do a lot of insecure stuff."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "Should this be done as part of `expireSnapshots`? I'd like to avoid adding a lot of operations to `Table` because it is already a large API."
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "I do not think that this type (and its constructor) have to be exported."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "why add this? don't think it's correct? for instance, it returns ErrCandidateNotExist (not critical), in this case we should return a receipt with corresponding status"
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to use `acme.ChallengeProvider` instead of `acme.ChallengeProvider` instead of `acme.ChallengeProvider`.",
      "reference": "Instead of creating a new file, put this in tls.go, like right after or before DNSProviderConstructor is defined."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Instead of OC.getLocale() for the default value the default should be the value of the user value 'core' 'lang'. When loading the page this can be added to the parameters by retrieving $this->config->getUserValue($user->getUID(), 'core', 'lang'); in viewcontroller.php."
    },
    {
      "prediction": "I think this should be a static pointer, not a static pointer.",
      "reference": "Why interface1 ? It should be in inner so."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with this, but I'm not sure if this is the right thing to do.",
      "reference": "Ideally, I'd have converted dicts to object but this way was less changes so this way for now."
    },
    {
      "prediction": "I don't think this is a bug in the compiler.",
      "reference": "Why is that test different to line 4022 (allocate is not tested there)? Shouldn't that be consistent?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should we consider move this expression evaluation to SETUP_INSERT step since it evaluates from queue entry. Also, this expression is not evaluated in ExHbaseAccessVsbbUpsertTcb."
    },
    {
      "prediction": "I don't think this is a bug in the Otlp enum.",
      "reference": "Don't see any more TODOs here.."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can you extract this out to a constant?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `verbose` argument?",
      "reference": "any testcase for saargs, and tidyargs argument processing?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "@ericstj do you think it is worth combining these two? With the presence of the message meaning it is enabled?"
    },
    {
      "prediction": "I think this should be skipped.",
      "reference": "why not use instance.RootDeviceName ?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "not needed, ADIOS2 also needs to check for subfiles. ADIOS2 tries to remove dependency on serial `fstream`."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "no need to wrap in new Promise - you can simply throw the exception"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Isn't this testing an implicit config, not a manual config?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I don't think this is used any more, please remove."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "shouldn't we name abbreviations up-cased? `myId` -> `myID`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This just always calls refs. I think we need to either hoist ref invocation back out of `setProperty()` (it used to happen during rendering), or wait for component recycling to go away."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Oof. I may have missed this while reviewing #3805"
    },
    {
      "prediction": "I don't think this is the right thing to do with `mex.h` and `mex.h`.",
      "reference": "why the NOLINTs here? please just alphabetize the headers (should be easier than adding NOLINTs) unless there's a good reason not to..."
    },
    {
      "prediction": "I don't think this should be a function.",
      "reference": "Should we maybe return `<svg />` instead?"
    },
    {
      "prediction": "I don't know how to use `cors.load_plugins`?",
      "reference": "Please use camelCase in new code"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Looks like the whitespace is off here. Not sure if there's a space or two too many or if there is an issue with tabs vs. spaces, but you probably want to fix this :)"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "This was just my laziness and I didn't copy the first line. Just remove it together with one empty line. Thanks"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `ProductDataFactory` and `ProductDataFactoryInterface`",
      "reference": "Why did you decide to change CartItemTest but you didnt change QueryBuilderWithRowManipulatorDataSourceTest?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This was sort of a pre-existing bug -- we should be busting our local cache if the key isn't present. However, `KBPKIClient.HasVerifyingKey` already took care of it on that path. This way is better though."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should this tag addition for generated files be handled explicitly in `private/model/cli/gen-api/main.go`"
    },
    {
      "prediction": "I'm not sure if this is a quiet time notification.",
      "reference": "You want to return if it's quiet time and notifications during quiet time are **not** enabled. So this is either a logic error or it's bad naming of the setting/field/method."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "Prefer double-quoted strings unless you need single quotes to avoid extra backslashes for escaping."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "cool, here (L146 && L148) maybe (repo_private? || force_private?) && !installation? to prevent double call of installation?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this error carries a bit more meaning for us, but less meaning for users. we also lose the context of what command produced the failure. I'd prefer to keep the original error message. If we need better identification of GetActiveApp errors, maybe we could address that in the error messages it returns?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Same: DO NOT USE IN PRODUCTION. Yes we should shout ;)"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea.",
      "reference": "This change may be hiding more errors, if we continue to see more."
    },
    {
      "prediction": "I don't think this is the right thing to do with this, but I don't think this is the right thing to do with this, but I don't think it's the right thing to do with this.",
      "reference": "Beware of exposing the underlying features directly. Any mutable fields should be reset per request."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This is probably more nuanced than I can feasibly check in a PR review, haha. Was the issue here that `replaceChild()` removes `initialBase` from the DOM before `recollectNodeTree()` invokes `componentWillUnmount()` on the owning component?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I believe it's misleading name for the condition. I prefer \"element_to_be_disable\" We can have a condition, when element is enabled but we can't click it, because another element overlays above it. So, If we use \"unclickable\" we might mislead people, who use that condition to verify if element can be clicked"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Do we need to expose it? It looks like it is only used in tests and only to obtain the final metrics. I think you can get the same by using `DataFile#lowerBounds` and `DataFile#upperBounds`. It seems `DataWriter` already exposes `toDataFile` that you can use."
    },
    {
      "prediction": "I think this should be a function, not a function.",
      "reference": "the test was failing likely due to locale issue. had to increment the date by 1 to make it pass"
    },
    {
      "prediction": "I don't think this is the case for the `levitate` attribute, but it's not the case for the `levitate` attribute.",
      "reference": "The changes below here can also be undone."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Instead of importing context besides beehivecontext, I'd suggest include golang context functionalities into beehivecontext. To keep channelq only rely on beehive."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I'm not sure about this one. Are you sure we don't need to initialize this fragment anywhere else?"
    },
    {
      "prediction": "I don't think this is the case.",
      "reference": "You didn't set a source here, so it will probably fail."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Might be easier to just do `handler{Handler: rpcHandler}` since zero-value of `Deps` is now valid."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Could you please add docs for this method?"
    },
    {
      "prediction": "I'm not sure if this is a real node, but it's not a real node.",
      "reference": "we should probably `@Deprecated` this implementation to be removed in PMD 7.0.0"
    },
    {
      "prediction": "I don't know how to use `powershell` or `powershell`?",
      "reference": "I wonder if 'unix' makes more sense for this now? I was thinking of putting up a 'cleanup' PR - I think I missed a few \"remote\" var names in the first PR, and want to reassess unifying the transport classes that just define `with_connection`. Renaming this could be part of that."
    },
    {
      "prediction": "I think this is a bug in Sarif 1.0.0-beta.5, but it's a bug in Sarif 1.0.0-beta.5, but it's a bug in Sarif 1.0.0-beta.5, but it's a bug in Sarif 1.0.0-beta.5, but it's a bug in Sarif 1.0.0-beta.5.",
      "reference": "Do something similar to what was done in JsonTests (can you derive from JsonTests?)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Yes, not much we can do here."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Why do we need this?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Would prefer to see an actual script here."
    },
    {
      "prediction": "I think this is a bug.",
      "reference": "seems reasonable to also want to include the 'to' location?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This change is unnecessary."
    },
    {
      "prediction": "I'm not sure why this should be used in the constructor, but I'm not sure why this is the right thing to do.",
      "reference": "Just as a note: Is it possible that the select css class is the same as the hover one? If this is true we should choose a different style for the selection css class, to make it more clear to the user I think."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "What about Secrets, are we not also trying to cover those?"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "(commit messge): how about > update internal commit API for RFC 11"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This will now wait for 2.5 hours, not 90 minutes, if the waiter delay is 5s"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "See this error on console too so I don't think it's just test simulation. For some reason event doesn't show up sometimes"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We're passing the same thing twice?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Shouldn't the value in Bootstrap.Data be just a plain string?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "@robertpi Isn't this changing the sampling priority when `KeepTraces==false`? The sampling priority could be `AutoReject` or `AutoKeep`, based on the sampling decision (or the user may have specified something else). Seems like we shouldn't be changing it in this case?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "The const can also be used in cloud/pkg/cloudhub/servers/httpserver/server.go L46-47?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Use a constant for `procedures_prototype`."
    },
    {
      "prediction": "I think this is a bug in the future.",
      "reference": "This file should probably not be touched as the formatting of the string seems to be a test in itself ?"
    },
    {
      "prediction": "This is a hack.",
      "reference": "style nit: missing leading '*'"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "The operationTracer is passed into the processTransaction() method. We should probably pass the no tracing in one in from where it is called."
    },
    {
      "prediction": "I don't know how to do this, but I don't know how to do this.",
      "reference": "I believe this line was an error, it should have been `sercomRXPad1` to be consistent with the pin numbers. Resolving this ambiguity by following the pin numbers."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do, but it's not the right thing to do.",
      "reference": "May be useful to have the reason here, though clearly not pressing."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "These were inverted before"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "DB is implemented in PR 951"
    },
    {
      "prediction": "I don't think this is a good idea, but it's not a good idea.",
      "reference": "move all constants to `pkg/util/constants.go`, these constants had been used in `volume_stats.go` file too. So better to import them."
    },
    {
      "prediction": "This file is covered by the GNU General Public License.",
      "reference": "Could you revisit the full header and add appropriate spaces after the hashes?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the code hint?",
      "reference": "This should either be `hint` that takes a string to render inside of the partial container or probably better you should just render a separate hint field above the code field in the same tab."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this was flapping"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Please add a check to see if SafeAreaInsets is available. It isn't on all iOS versions."
    },
    {
      "prediction": "I'm not sure why this is the right thing to do here.",
      "reference": "interpolation here was causing the translation to not get picked up"
    },
    {
      "prediction": "I don't think we need to remove the writer from AsyncWriterThread.",
      "reference": "We don't need to disable the flow controller here as in `StatefulWriter`s destructor?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "I would rather no have this as a `kwarg` as it encourages \"growth\" which lead to an unweildy constructor in other classes. Let's add a method or property to take care of this instead as I think it's usage is going to be quite low."
    },
    {
      "prediction": "I don't think this is the right thing to do with the IPVS connection.",
      "reference": "I just noticed that we use Return here, when we have logically allowed a packet, whereas in the forward chain we use AcceptAction. Do you know why that is?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do?",
      "reference": "There's one for floats but not for ints. The float implementation is non-trivial though which I guess is the argument there."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "If we have a redirection policy for Selected API forwarding, why isn't \"redirect all\" just a special case where they are all Selected?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I wouldn't add this. Just completely ignore config if custom reporter is not `nil` in server options."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "What's the meaning about the code?"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Would this incorrectly trigger if `loadingUrl.getHost() = \"something.app\"` and `bridge.getHost() = \"app\"`?"
    },
    {
      "prediction": "I think this is not the case when using `IoULoss`, `GIoULoss`, or `DIoULoss`",
      "reference": "Note generally it -> It"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Does this mean that every call to `configSet.getIndexSchema()` will create a new schema object (if shared schema is not enabled)?"
    },
    {
      "prediction": "This file is not used by anyone who may use this file.",
      "reference": "License header should use the Apache one."
    },
    {
      "prediction": "I think this is not a good idea, but it's not a good idea.",
      "reference": "I think this makes more sense to be applied within the parser code where we evaluate the `glob` builtin? This function looks generic in the sense of where it can be used, and perhaps no matches is fine in other cases?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "should we validate that AWSRegion has also been set here so that we don't get into the if-block that relies on the ec2 metadata client below?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "maybe naming `version` to `package_version` or something similar can be more descriptive"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why was this changed?"
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Should not have snuck in here right? This is a golang 1.17 feature, wii definitely want to update these"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Pundit is unaware of namespacing, however you can still create the class under policies/org_admin/plans_policy.rb. That means, the condition for the unless can be reused in other places too. You would call the policy as OrgAdmin::PlansPolicy.new(current_user).index? after that unless"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "this warning shouldn't be produced if we configured a cache either"
    },
    {
      "prediction": "I'm not sure if this is a change-stream.",
      "reference": "what if the collection is already there?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "instead of removing can you reference org.openqa.selenium.TakesScreenshot ?"
    },
    {
      "prediction": "I'm not sure why this is the case, but I'm not sure why this is the case.",
      "reference": "Please revert unrelated changes"
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "As far as I know, this will replace only first occurance of Countly, not others, if there are more than one Countly word in localized string"
    },
    {
      "prediction": "I don't think this is the right thing to do with the name?",
      "reference": "I suggest, that we move the regex (`[^a-zA-Z0-9_]`) to a separate constant field, because we're using it in multiple places and I think it's quite prone to misspellings."
    },
    {
      "prediction": "I'm not sure why this is needed?",
      "reference": "Feel free to disregard, but I've been trying to use `Mapping` and `Sequence` instead of `Dict` and `List` when possible, because they communicate that the type is immutable, and also are covariant."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `github.com/nats-io/nats.go` or `github.com/nats-io/nats.go` or `github.com/nats-io/nats.go` or `github.com/nats-io/nats.go`",
      "reference": "No need for blank line here. This block will then be reordered alphabatically."
    },
    {
      "prediction": "I don't think this is a bug in the client-go package.",
      "reference": "let's call it `in-cluster` instead of `local`. less chance of confusion."
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "Please use camelCase instead of underscore_case"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Ideally, we'd fold the schema into an expanded system_meta, but this is a good first step."
    },
    {
      "prediction": "I think this is a bit of a hack, but it's a bit of a hack, but I'm not sure if this is the case.",
      "reference": "Is this used?"
    },
    {
      "prediction": "I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Should we use `#if NETFRAMEWORK` for consistency with the other projects?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If it parses failed, both of the `containerName` and `podId` should be the empty strings, it's non-sense to define this error, I suggest just return it."
    },
    {
      "prediction": "I'm not sure if this is the case with the `testApplicationId` and `testApplicationId` are the same as the `testApplicationId` and `testApplicationId` and `testApplicationId` are the same as the `testApplicationId` and `testApplicationId` and `testApplicationId` are the same as the `testApplicationId` and `testApplicationId` and `testApplicationId` are the same as the `testApplicationId`",
      "reference": "line 26 can be removed i think > applicationId: or('config.unsplashAPI.applicationId', 'settings.unsplash.applicationId'),"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "To generalize for possible future new enum options."
    },
    {
      "prediction": "I don't know why this is needed?",
      "reference": "Shall we remove this variable at the end of UTScapy execution?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "What is this checking for? Why is returning the list of interfaces the correct behaviour in this case?"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Please name it correctly as Beam ;)"
    },
    {
      "prediction": "I think this is not a valid error.",
      "reference": "After chatting with Andrew, we think it's better to look for this particular error string that is causing issues (\"connection reset by peer\") instead of blindly retrying on any error we don't know about."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "any reason to not have defaults here like you had before? (ARM)?"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `page_info.current_page`?",
      "reference": "This is a change. The old code was just wrong before, but now here (and one other machine-readable place) we expose the start index as 0 for the first item."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This changes the behavior of the parser, right? Any particular reason to do this aside from the fact that you have to since the function takes a const?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `createPortal(...)` method.",
      "reference": "Given how simple the Portal implementation is, I wonder if we should move it core... Though we'd have to export it which would be more bytes we can't crawl back..."
    },
    {
      "prediction": "I'm not sure if this is a clone of the original schema, but it's a clone of the original schema.",
      "reference": "The more correct way of doing this is `this.s.hooks.clone()` but either way works. Thanks for finding this :+1:"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Can we update bool to an enum instead of a string? This helps future extensibility"
    },
    {
      "prediction": "I don't think this is the right thing to do with the time zone.parse('2015-10-01') or Time.zone.parse('2015-10-01') or Time.zone.parse('2015-10-01') or Time.zone.parse('2015-10-01') or Time.zone.parse('2015-10-01') or Time.zone.parse('2015-10-01') or Time.zone.parse('2015-10-01'",
      "reference": "Should we share, since this is also being used with gsa18f?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "There can be multiple subrows, so it is not a good idea to use `id` there, as id should identify single unique element. Instead you could just add the id of whole table or of whole crash plugin view"
    },
    {
      "prediction": "This is a hack.",
      "reference": "Why was this assert removed? Shouldn't we check if the file is in the zip?"
    },
    {
      "prediction": "I don't think this is a problem.",
      "reference": "This logic should be handled at informer handle functions i.e. AddFunc, UpdateFunc, DeleteFunc"
    },
    {
      "prediction": "I don't think this is the right thing to do with `IsStripePoolSpec(poolSpec)` and `IsStripePoolSpec(poolSpec.RaidGroups[0].Type)` and `IsStripePoolSpec(poolSpec.RaidGroups[0].Type)` and `IsStripePoolSpec(poolSpec.RaidGroups[0].Type)`",
      "reference": "S1008: should use 'return <expr>' instead of 'if <expr> { return <bool> }; return <bool>' (from `gosimple`)"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Just to remove branching, use `defaultTitle` explicitly in the test cases. (Is this gofmt'd?)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I don't think you use this variable anywhere. (You call `SampleTransformer.newBuilder()` below)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The digest is in binary and variable size (the digest size is result if > 0). So we can't use xxstrdup."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "We don't need this additional method."
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "We can't do this. Adding a method to an interface is a breaking change. This was an oversight on our part when we converted ClientConfig from a struct to an interface. OutboundConfig was introduced to fix this, the idea being that we should use OutboundConfig everywhere instead of ClientConfig. In case of Dispatcher, we want to use the OutboundConfig and MustOutboundConfig methods instead of ClientConfig, and for streaming, the client needs to attempt to upcast a ClientConfig to OutboundConfig and error out if that's not possible."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Why not using the constant `PARTICIPANT_QOS_DEFAULT` here?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Shouldn't this be `tm_cpp` to match `temporalImp`? (There are multiple CPP implementations, so 'cpp' is ambiguous.)"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Need to remove this empty line for rubocop to be happy."
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "just checking: do we need to remove this because otherwise the `List` operations may not return the entire set of Pods / Namespaces? do you know why we used `alwaysReady` in the first place, I can't remember?"
    },
    {
      "prediction": "I think this is a hack, but it's not a good idea to use `mongodb://localhost:27020/?serverSelectionTimeoutMS=1000` and `mongodb://localhost:27020/?serverSelectionTimeoutMS=1000` and `mongodb://localhost:27020/?serverSelectionTimeoutMS=1000` and `mongodb://%2Ftmp%2Fmongocryptd.sock/?serverSelectionTimeoutMS=1000`",
      "reference": "maybe we can replace `mongoClient.s.options.autoEncryption.cryptdConnectionString` with `options.autoEncryption.cryptdConnectionString`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "But we're already doing os_switch_lib_tls to app a few lines above, so there is now redundancy we should alleviate."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Under what circumstance would we have a span id already? Is this for testing purposes?"
    },
    {
      "prediction": "I don't think this is the case for a non-signaling semaphore.",
      "reference": "The original text can be read to say \"not waited on by queue ...\" meaing that the second queue was supposed to have *waited* for the signal... which is especially confusing when it's the same queue that has signalled the semaphore *twice* without a wait."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "just clarifying the error messages a bit."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Have those (and other data like conf...) shared across tracers?"
    },
    {
      "prediction": "I don't see the License at this point, but it may be useful if you don't have a copy of the License at this point.",
      "reference": "could we add this file only when we need one?"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "This may not even be needed."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Capitalisation seems inconsistent here?"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure why this is the case.",
      "reference": "maybe better Error(string text) and Error(Exception ex) separately?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "can you leave the old one in too please? at least for now, otherwise anyone using it now will break."
    },
    {
      "prediction": "I'm not sure if this is a PVPCreature, but I'm not sure if this is a PVPCreature.",
      "reference": "Trailing tab, remove it in another PR."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "what about merging the error checking logic to within `errShouldUnload`?"
    },
    {
      "prediction": "I don't know why this is needed.",
      "reference": "Probably want Topic.find_by_slug! to handle bogus topics. The next line will try to load articles off of nil otherwise."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Should it really be done on test side?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "Can we elaborate on why? I'm guessing because we need the execution role to call FE stopTask during `cleanupTask`, but would be good if we make it clear here."
    },
    {
      "prediction": "I think this is a bug in Cobra.",
      "reference": "is there a reason why this is not called from inside `validate`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": ":+1: I much prefer this style for functions with more than a few arguments."
    },
    {
      "prediction": "I'm not sure why this is a bug?",
      "reference": "Are these mutually exclusive options (parameters vs qualifiers)? If parameters aren't supported, may want to consider throwing an exception for \"hasParameters\". If parameters and qualifiers are both legit options, then maybe change this to `if (hasQualifiers) { ... } if(!hasQualifiers && !hasParameters)`"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "Why did you remove this line?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Very unclear error message. Remember that these are messages that your users see. Please be more specific"
    },
    {
      "prediction": "I don't think this is the right thing to do here.",
      "reference": "Can we add these when we need them  "
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure if this is the case.",
      "reference": "I believe you can simplify this to simply `return array_unique(array_filter($authors));` -- the default behavior of array_filter is to filter out empty elements, so the callback should not be required in this situation. Do you mind giving it a try and updating the PR if it works?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the UIAElement.",
      "reference": "Would it make sense to log a debug warning here?"
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "\"in the keystore\", but nevermind"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "This should be done in a separate PR."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do?",
      "reference": "Rather than this maybe `Text.sanitize` would be better here"
    },
    {
      "prediction": "I'm not sure why this is the case. I'm not sure if this is the case.",
      "reference": "lot of places setting default 'false' to static value - noise in PR"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "I think you should use `$event->getOriginalFileUrl()` instead of `$sourceFilePath` here."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "nit: It's a matter of taste, but it would be tighter if this is called `api_quota`."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "I noticed in all of these we now have to import the PrecompiledContract under testing. Could also rename the package these are in s/precompiles/precompile to keep them in the same package as they are elsewhere."
    },
    {
      "prediction": "I think this is a hack, but I think it's not necessary to use the `hdfs_version` and `effective_user` in the config.",
      "reference": "doubt this matters..."
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with the `scapy.layers.all` module.",
      "reference": "Gets updated versions of `LOOPBACK_INTERFACE`, `LOOPBACK_NAME` when importing scapy."
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "checking for ref. equality is probably fine here, but it takes a reader longer to navigate the code and figure out whether ref equality is really wanted here vs just using `equals()`"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "looks like it's not used? Do we plan to use it in the future?"
    },
    {
      "prediction": "I think this is a hack, but I think it's a bug in statsd exporters.",
      "reference": "I think this is an unrelated remark. I thought we had moved toward the practice of using \"Config\" as the structure name, and Option as a functional argument (`func(*Config)`), and Options as a `[]Option`. See api/trace `StartConfig` and `StartOption`, for example. That's why I prefer this struct be called Config."
    },
    {
      "prediction": "I don't think this is a hack, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "nitpick: superfluous parenthesis"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "If, for a given integration, the tag/measure is always set, it should be added to the strongly-typed tags (here for instance, in GraphQLTags). This way, the underlying dictionary is allocated only in the rare case where users add custom tags"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "The position change of this line may be a hard fork."
    },
    {
      "prediction": "I think this is a bug in pugi.js.",
      "reference": "id is unsigned  "
    },
    {
      "prediction": "This is a hack.",
      "reference": "It looks like Puppet doesn't provide type validation for options and we don't provide it ourselves as part of the function. Is that something we'd want to do at some point?"
    },
    {
      "prediction": "I'm not sure if this is a static table scan. I'm not sure if this is a static table scan. I'm not sure if this is a static table scan. I'm not sure if this is a static table scan. I'm not sure if this is a static table scan. I'm not sure if this is a static table scan. I'm not sure if this is a static table scan. I'm not sure if this is a static table scan.",
      "reference": "Looks like this didn't need to change."
    },
    {
      "prediction": "I'm not sure if this is the case, but it's not the case. I'm not sure if this is the case.",
      "reference": "I don't understand why this is here and what's the intention with it? Can you elaborate what's the reasoning behind this change?"
    },
    {
      "prediction": "I think this is a bug in sqlplugin.",
      "reference": "I think @sergeybykov converted (wanted to convert) all `shardID` to `int32` from `int64`. Please check with him."
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "This will only fix client side (so showing it in-game) server still gonna hold invalid values I guess?"
    },
    {
      "prediction": "I don't think this is the right thing to do with a DynamicMap.",
      "reference": "Shouldn't this be `cls.param.warning`?"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "This spec can be modified, giving you extra strength (Check this fetch key doesn't work and therefore returns `nil`)"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Could we not just always include `self.config.options.listen_host`? If that is empty, the `address[0]` check should also never be true."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Why not just access `ops` directly like before?"
    },
    {
      "prediction": "I think this is a bit of a hack.",
      "reference": "Is there even a need to keep the bool?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "wrap to stay under 80 characters"
    },
    {
      "prediction": "I don't think this is a problem?",
      "reference": "`return NULL` is more clear than `throw` at least in my reading, and consistent with #3362."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Both of these are important. Without it, locust won't find my libraries in the cloud."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This should remain as `ListServices`"
    },
    {
      "prediction": "I don't think we want to use `-0,0 +1,2` in the `-0,0 +1,2` in the `-0,0 +1,2` in the `-0,0 +1,2` in the `-0,0 +1,2` in the `-0,0,1`",
      "reference": "If no tests, remove this file."
    },
    {
      "prediction": "I think this is a bug in the protoc.",
      "reference": "This will require changes to the docs. I suggest searching the gh-pages branch for the previous variable name."
    },
    {
      "prediction": "I don't think this is a bug in the kernel.",
      "reference": "`RemoteHandler` is used in nvda_slave and slave does not have access to `globalVars` currently. Perhaps `globalVars.appDir` should be set to `None` in `globalVarrs by default and set to NVDA directory when they're imported for the first time."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "In case there is more configuration to be added to the \"inmem\" metrics later (however unlikely that is), we may want to play it safe and create an `InMemConfig` struct and include the disabled flag there. This also gives the config symmetry across the plugins."
    },
    {
      "prediction": "I'm not sure if this is the case, but it would be better to do this. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "I'll need to pull this out of here since we're sharing this in other tests. Same for `procurement_spec.rb`"
    },
    {
      "prediction": "I don't think this is the right thing to do with the user.",
      "reference": "what about `observer` as a var name here (and below) rather than `obs` ? -- would be clearer, imo!"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `message` property.",
      "reference": "could you change this to instead of being a `try.. except` be `message = message.get('message')`"
    },
    {
      "prediction": "This file should not be used in the project root.",
      "reference": "Add space between License and nameapace"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do.",
      "reference": "should we have a `before_filter` for auth here?"
    },
    {
      "prediction": "I think this is a bug in the ELB.",
      "reference": "@vincepri I know we discussed moving this up and only calling it once, but I didn't (quickly) see an easy way to generate the right event based on the appropriate action (attach vs detach). Happy to move it around if you have suggestions."
    },
    {
      "prediction": "I'm not sure how to do this?",
      "reference": "Can we use record.update here?"
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "Shouldn't the exact case option matter here?"
    },
    {
      "prediction": "I don't think this is the right thing to do with the `parent_cls` and `parent_cls` and `parent_cls` and `parent_cls` and `parent_cls` and `parent_cls`",
      "reference": "Errr, why haven't we noticed this until now?"
    },
    {
      "prediction": "I think this should be removed in the future.",
      "reference": "It's a little spooky that this method throws exception if you try to set the attribute to a different value than it was set before, but then does leave the new value set in the attributes?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Please only increment by 1."
    },
    {
      "prediction": "I don't think this is a bug.",
      "reference": "Sorry I might have missed some context, but what's the reason you choose `Period` over `Duration` or `Interval`? (Thumbs up for using `org.joda.time` instead!)"
    },
    {
      "prediction": "The `preventWheel` option is deprecated.",
      "reference": "Please check if is it possible to mark it as private. What's more please add this to the TypeScript definition file."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Maybe move this to `util.h` ?"
    },
    {
      "prediction": "I'm not sure if this is the right thing to do with `golang.org/x/net/context`?",
      "reference": "oops. this won't work will it"
    },
    {
      "prediction": "I think this is the case where we don't know how to do this.",
      "reference": "@strib I assumed this is what you meant; but let me know if I'm wrong!"
    },
    {
      "prediction": "I don't think this is the case for the first command for this instance.",
      "reference": "I believe the error has changed"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Lint/UnneededDisable: Unnecessary disabling of Naming/PredicateName."
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Should this be removed now?"
    },
    {
      "prediction": "I think this is a bug in the code.",
      "reference": "streamHandle sounds vague to me. Can you be more specific?"
    },
    {
      "prediction": "I don't think it's a `cursorState` property, but it's a `cursorState` property.",
      "reference": "Does everything on cursorState belong in the command options?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This is clever, but I do admit I think it's kinda weird. We can go with it for now and fix it later if people complain."
    },
    {
      "prediction": "I don't think this is the right thing to do with `gs://`?",
      "reference": "the variable names are not entirely clear. \"bucket\" is essentially the regex that follows gcs naming pattern, right? if so, it should be changed to bucketregex. and then bucketregex, gsregex should be changed to something more specific to what pattern the regex is supposed to match."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "I think `ApiModelT` would be clearer than `T`"
    },
    {
      "prediction": "I think this is a bug in RDKit.",
      "reference": "Shouldn't this be 2019?"
    },
    {
      "prediction": "I think this is a bug in the containerized flow.",
      "reference": "We should consider giving this state a more generic name which could be used for flows in similar state in non-containerized Azkban. For instance in the event of a bare-metal executor crashing we could the switch any flows assigned to that executor to this state. Something like `EXECUTE_INFRA_FAILED`, better alternatives should be possible though."
    },
    {
      "prediction": "I don't think why this is the right thing to do?",
      "reference": "This should allow `role=definition` and `role=term`, possibly also `role=list`?"
    },
    {
      "prediction": "I don't think this is the default value.",
      "reference": "Should this use `boolean` instead of `Boolean`?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Currently in our Zipkin tests, only one passed parameter would instantiate a Resource and checks for its tags populating. I left the If(UseTestResource) clause in the code in case we would like to return to the old resource tag checking, but if it makes more sense I can remove that parameter entirely."
    },
    {
      "prediction": "I don't think this is the case. I'm not sure if this is the case.",
      "reference": "While this is potentially convenient it seems off topic for the PR/Issue. Also if it is kept, in the realm of taste/style I tend to not use get/set/is for things that are not properties of the object. maybe hasLiveNode(String node) thus someone using it might write `if (zkReader.hasLiveNode(\"foo\")) ...` which reads quite nicely."
    },
    {
      "prediction": "I don't think this is a good idea.",
      "reference": "What's the difference between blogSvid and the SVID above? Looks like the functions that use these aren't being called currently - can they be removed?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "can you add numbers with this change? the CLI is a javascript engine and it can worh number - java adds strings vi concatenation"
    },
    {
      "prediction": "I'm not sure if this is the case.",
      "reference": "Shouldn't this `TEXT` also be dependent on the platform, then?"
    },
    {
      "prediction": "I don't think this is a bug in the interpreter package.",
      "reference": "Can we name this `TableObject`? I'm not a big fan of the `I` prefix for interfaces and that's not really used in Go. Is it also possible to have the method be unexported? I don't know if that's possible. If it's not, this is good. If it is possible, I'd prefer this method to be unexported."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "If tbb.h is included, there is no big sense to include other TBB headers."
    },
    {
      "prediction": "I don't think this is a good idea, but I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Let's use the same `S3_HOSTNAME_PATTERN` as above here."
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "This shouldn't be here."
    },
    {
      "prediction": "I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string, but I'm not sure if it's a string.",
      "reference": "A `case` statement may be simpler here."
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "why are we adding the current tag count to new tag count ?"
    },
    {
      "prediction": "I don't think this is a hack.",
      "reference": "Are you writing \"none\" to file content? no good"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with this class, but it's not the right thing to do with it.",
      "reference": "Should we allow `string|string[]` here?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "Is there a reason for logging `error.message` specifically, maybe log the whole error object?"
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case. I'm not sure if this is the case.",
      "reference": "Why is this needed?"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "Nothing. We only expect container-connected events when going via the plugin, not the proxy."
    },
    {
      "prediction": "I'm not sure if this is the case, but I'm not sure if this is the case.",
      "reference": "We might want to introduce some randomness here in case there are multiple completely separate Preact installations running, i.e. 2 widgets as those will be two roots with a resetting `_domDepth`"
    },
    {
      "prediction": "I think this is a bug?",
      "reference": "this seems a bit wrong no? why is this change needed?"
    },
    {
      "prediction": "I think this is not a good idea.",
      "reference": "Still confusing. Why don't we return something like `'Fee too low: expected X but found Y'`?"
    },
    {
      "prediction": "I think this is a bug in Wireguard.",
      "reference": "Should be from lowercase `json:\"ports\"` the same is defined in MarshalJSON"
    },
    {
      "prediction": "I don't know how to do this with the `sns-ruby-example-create-subscription.rb`?",
      "reference": "Simple Notification **Service** (singular)"
    },
    {
      "prediction": "I'm not sure why this is the right thing to do with the `nashornEngineFactory` and `nashornEngineFactory` and `nashornEngineFactory` and `nashornEngineFactory` and `nashornEngineFactory` and `nashornEngineFactory.createEngine` and `nashornEngineFactory.createEngine` and `nashornEngineFactory`.",
      "reference": "This code should be executed in NashornEngineFactory"
    },
    {
      "prediction": "I think this is a hack.",
      "reference": "this is not so great as it sets the global rand seed. in tests that invoke this method multiple times for whatever reason, the global seed would be overridden every time the constructor would be called and the instances would have a different seed after every constructor call. it would be better to just pass a new source here as a parameter and do the same within the test. it should simplify things and clean this up"
    },
    {
      "prediction": "I think this is the default value for `unprotectedTransactionsAllowed` and `unprotectedTransactionsAllowed` is the default value for `unprotectedTransactionsAllowed` and `unprotectedTransactionsAllowed` is the default value for `unprotectedTransactionsAllowed` and `unprotectedTransactionsAllowed` is the default value for `unprotectedTransactionsAllowed` and `unprotectedTransactionsAllowed` is the default value for `unprotectedTransactionsAllowed` and `unprotectedTransactionsAllowed` and `unprotectedTransactionsAllowed`",
      "reference": "This looks inverted to me: if `--rpc-require-chainid-in-txs=true`, then shouldn't `unprotectedTransactionsAllowed == false`? Suggest changing this variable to `requireTxReplayProtection` or similar. I think the flag name could be clearer as well, maybe: `--require-tx-replay-protection`."
    }
  ]
}