diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index 12fde841f97dc8066c312cf05c426c91b26c6cf1..7d4fa7fdb241ef6a951c107edeabc5cec99c2086 100644 --- a/analysis/current/analysis-report-hybrid.json +++ b/analysis/current/analysis-report-hybrid.json @@ -1,8 +1,8 @@ { "schema_version": "1.0", "repo": "huggingface/transformers", - "snapshot_id": "20260509T060023Z", - "generated_at": "2026-05-09T06:08:25Z", + "snapshot_id": "20260509T120021Z", + "generated_at": "2026-05-09T12:04:05Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1426,7 +1426,7 @@ "cluster_id": "cluster-43824-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", "status": "open", - "confidence": 0.55, + "confidence": 0.75, "canonical_issue_number": 43824, "canonical_pr_number": 43836, "issue_numbers": [ @@ -1437,7 +1437,8 @@ 43842 ], "evidence_types": [ - "closing_reference" + "closing_reference", + "shared_issue_target" ], "pr_comparisons": [ { @@ -2004,7 +2005,7 @@ 43842 ], "target_issue_number": 43824, - "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference evidence." + "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." }, { "cluster_id": "cluster-43979-11", diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index cbf6b14014af42ec4ea5be54fb23230d25cf8213..e94706a15634edca6b91dd3a73d9f890b707eecf 100644 --- a/analysis/current/analysis-report-hybrid.llm-reviews.json +++ b/analysis/current/analysis-report-hybrid.llm-reviews.json @@ -1,8 +1,8 @@ { "schema_version": "1.0", "repo": "huggingface/transformers", - "snapshot_id": "20260509T060023Z", - "generated_at": "2026-05-09T06:08:25Z", + "snapshot_id": "20260509T120021Z", + "generated_at": "2026-05-09T12:04:05Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -13,8 +13,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-13244-3", "nodes": [ @@ -84,8 +84,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -644,8 +644,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -987,8 +987,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -1418,7 +1418,7 @@ "issue:38175|issue:43994", "issue:43632|issue:45834" ], - "prepared_review_unit_hash": "ec1c330d7505ce56e01e73a984b56d7596b6e927335eff3f8dcf6090200e5f81", + "prepared_review_unit_hash": "4b607d2ec926aaab8873b57691419f0a7c960514b90f29db57d09a5c35e7f423", "component_budget": { "node_count": 392, "item_count": 392, @@ -1440,213 +1440,213 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most of the cluster is a collection of separate bug reports that only share broad theme words. The strongest duplicate set is the `_is_hf_initialized` regression pair, and the custom-model initialization pair also looks like the same bug. The siglip2 pair is plausible but too thinly supported from titles alone, so I would not merge it here.", - "confidence": 0.76, - "canonical_issue_reason": "issue:44291 is the clearest direct report of the `_is_hf_initialized` TypeError during `init_empty_weights`; issue:43872 looks like the same incompatibility surfacing through bitsandbytes.", + "summary": "The set is mostly heterogeneous, with a few loose thematic mini-clusters (custom model init/_is_hf_initialized, Qwen3.5 attention/position_ids, ZeRO-3 loading, tokenizer loading), but no strong duplicate group overall. No PRs are present.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43646 is the broadest, most generic report in the custom-model-initialization regression family, so it is the best provisional issue canonical; however, the cluster is too mixed to treat this as a true single-duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44291 is the best issue anchor because it names the specific failure path and can reasonably absorb issue:43872 as a related symptom report.", + "best_issue_reason": "issue:43646 is the closest thing to a cluster representative because it captures the general Transformers 5 custom model initialization breakage without narrowing to a specific environment.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Same broad model-loading space, but different models and different failure modes." + "reason": "Different models and failure modes: Qwen3 MoE conversion vs an Ovis2 checkpoint corruption report." }, { "left": "issue:43940", "right": "issue:45313", "accept": false, - "reason": "Both involve DeepSpeed weight loading, but the titles point to different models and not the same concrete bug." + "reason": "Both are ZeRO-3 loading failures, but they appear model-specific and not the same concrete bug." }, { "left": "issue:45161", "right": "issue:45823", "accept": false, - "reason": "Different model families and different code paths: TP support vs device-map forward mismatch." + "reason": "Tensor-parallel GPT-OSS MoE issue vs Gemma4 device-map mismatch; unrelated code paths." }, { "left": "issue:43872", "right": "issue:44291", - "accept": true, - "reason": "Both describe the same `_is_hf_initialized` incompatibility during model loading; 43872 is a downstream bitsandbytes symptom of the 44291 regression." + "accept": false, + "reason": "Shared `_is_hf_initialized` theme, but one is bitsandbytes constructor incompatibility and the other is `init_empty_weights` loading." }, { "left": "issue:41553", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer/loading issues, but they involve different models and different reported failures." + "reason": "Both concern tokenizers, but one is a bad error message and the other is a real loading regression for a different model." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "Different mechanisms: FineGrainedFP8Config failure vs `_is_hf_initialized`/bitsandbytes incompatibility." + "reason": "FP8/Qwen3Moe failure and bitsandbytes `_is_hf_initialized` incompatibility are distinct bugs." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "Both are model-loading problems, but the titles do not indicate the same architecture or failure path." + "reason": "Both are model loading problems, but they involve different architectures and likely different fixes." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Trainer signature mismatch vs mask/tensor shape mismatch are unrelated bugs." + "reason": "Trainer API keyword mismatch vs tensor mask shape mismatch; no shared code path." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "Both mention attention-related failures, but the concrete code paths differ too much." + "reason": "Both touch attention behavior, but one is Qwen3.5 RLHF NaNs and the other is a flash-attention `s_aux=None` crash." }, { "left": "issue:43257", "right": "issue:45305", "accept": false, - "reason": "Both are training regressions, but one is MoE weight conversion and the other is gradient averaging." + "reason": "Both are training-related, but one is missing Qwen3 MoE weight conversion and the other is gradient averaging with GAS." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Tokenizer/loading issues, but different models and different symptoms." + "reason": "Different tokenizer-loading problems for different models; not the same bug." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "`_is_hf_initialized`/bitsandbytes incompatibility is unrelated to CLIPTokenizer max-length behavior." + "reason": "`_is_hf_initialized`/bitsandbytes incompatibility is unrelated to CLIPTokenizer's absurd `model_max_length`." }, { "left": "issue:44530", "right": "issue:44863", "accept": false, - "reason": "PagedAttentionCache/Qwen3.5 crash and NemotronH checkpoint loading are different bugs." + "reason": "PagedAttentionCache group-type crash and NemotronH checkpoint loading failure are unrelated." }, { "left": "issue:41093", "right": "issue:44805", "accept": false, - "reason": "Similar shape-mismatch wording, but no evidence they are the same underlying bug." + "reason": "The error text is similar, but there is no evidence these are the same underlying mask-shape bug." }, { "left": "issue:44479", "right": "issue:44560", "accept": false, - "reason": "Both are video regressions, but the models and failure modes differ." + "reason": "Both involve Qwen variants and video/position handling, but they are different regressions with different symptoms." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "DeepSpeed training error vs image processor void-segmentation failure are unrelated." + "reason": "Training with DeepSpeed and void segmentation map processing are unrelated." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "Different model/runtime problems: GPT-OSS GGUF support vs dtype mismatch for Phi-tiny-MoE." + "reason": "GGUF GPT-OSS support and Phi-tiny-MoE autocast dtype mismatch are different issues." }, { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Same model family, but different code paths and symptoms." + "reason": "Gemma4 FSDP2 shared_kv_states bug vs Gemma4 PLE device mismatch; separate failures." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "GPT-OSS GGUF support and Qwen3-MoE sliding-window behavior are unrelated." + "reason": "Both mention Qwen3/GPT-OSS style models, but one is GGUF support and the other is sliding-window behavior." }, { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "Buffer handling regression and OCR index error are different bugs." + "reason": "Non-persistent buffer corruption and Kosmos2.5 OCR index error are unrelated." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Both are attention-related, but the model and failure mechanism differ." + "reason": "Both concern Qwen3.5 and attention, but one is torch.compile+SDPA and the other is flash-attention position_ids handling." }, { "left": "issue:43645", "right": "issue:43646", "accept": true, - "reason": "These read like the same Transformers 5 custom-model initialization regression, with 43645 adding a Jupyter-specific reproduction." + "reason": "These look like the same Transformers 5 custom-model initialization regression, with one being a notebook-specific manifestation of the same bug." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "GPT-OSS GGUF support and Float8 storage lookup are unrelated." + "reason": "GGUF GPT-OSS support and missing Float8 storage are different compatibility problems." }, { "left": "issue:43950", "right": "issue:45325", "accept": false, - "reason": "Non-persistent buffer regression and Qwen2.5-VL rope-index scaling are different issues." + "reason": "Buffer corruption regression vs Qwen2.5-VL rope-index scaling bug; different code paths." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "Different Qwen3.5 video/embedding failures with distinct code paths." + "reason": "Both mention Qwen3.5 video/input handling, but one is a StopIteration video error and the other is embedding unpacking with TRL SFT." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Missing import for a specific class is not the same as meta-device loading failures." + "reason": "Missing import for a specific model class vs meta-device loading breakage; not the same defect." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Qwen3MoE FP8 failure and meta-device loading regression are different bugs." + "reason": "FP8/Qwen3Moe and meta-device loading failures are different issues." }, { "left": "issue:42617", "right": "issue:43366", "accept": false, - "reason": "3d_parallel.py execution failure and GPT-OSS GGUF support are unrelated." + "reason": "Cannot run 3d_parallel.py and GGUF GPT-OSS support are unrelated." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer mapping failure and Gemma4 device mismatch are different bugs." + "reason": "Tokenizer mapping bug and Gemma4 PLE forward device mismatch are unrelated." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "GenerationMixin import error and Qwen3MoE FP8 failure are unrelated." + "reason": "Importing GenerationMixin and Qwen3Moe FP8 failure are unrelated." }, { "left": "issue:38175", "right": "issue:43994", "accept": false, - "reason": "They mention the same SigLIP2 model, but the packet only gives title-level similarity; that's not enough to confirm the same underlying bug." + "reason": "Both involve siglip2, but one is zero-probabilities behavior and the other is nonsensical AutoModel/pipeline output." }, { "left": "issue:43632", "right": "issue:45834", "accept": false, - "reason": "`_is_hf_initialized` regression and Kosmos2.5 OCR indexing error are unrelated." + "reason": "`_is_hf_initialized` flag regression and Kosmos2.5 OCR long-input indexing are unrelated." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The cluster call is not fully grounded in the packet. The main overreach is describing issue:44291 as having a \"concrete reproduction and version scope\" and calling it the \"root-cause\" report; the packet only provides titles/body lengths, not the issue text needed to support those claims. The `_is_hf_initialized` link between 43872 and 44291 is plausible and conservative, and 43645/43646 also looks reasonable, but the summary should avoid asserting stronger causal/root-cause language than the packet supports. The 38175/43994 accept is also a bit more speculative than the others because it relies only on same-model wording." + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative about the cluster being mixed. The chosen representative/canonical issue (43646) is reasonable, the one accepted soft-edge pair (43645\u201343646) is supported by the titles and appears mergeable as the same bug, and the rejection reasons for the other pairs do not overstate similarity. No PRs are present, as stated." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -1745,7 +1745,7 @@ "issue:45276|issue:45335", "issue:43404|issue:43454" ], - "prepared_review_unit_hash": "4b51de2c7f8a9b08909163ffc19205333f71c83740bb1899801ecf8618ee6579", + "prepared_review_unit_hash": "230ca532b7367ac1ff35c6c1f129eb0e21193ca676efca0acc9278ecf032a488", "component_budget": { "node_count": 392, "item_count": 392, @@ -1767,210 +1767,204 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous issue reports, with only a couple of clear duplicate-like pairs: the v5 non-persistent buffer regression and the resize_token_embeddings propagation bug. The rest are related by broad subsystem, model family, or symptom class but not the same concrete underlying bug.", - "confidence": 0.81, - "canonical_issue_reason": "Issue 44534 is the cleanest umbrella report for the exact non-persistent-buffer regression and is the best representative duplicate target in this cluster.", + "summary": "This cluster is mostly a collection of distinct Transformers regressions; only one pair is a clear duplicate. The strongest canonical issue is the non-persistent-buffer junk regression, with the later issue being a near-verbatim repeat.", + "confidence": 0.78, + "canonical_issue_reason": "Issue 43644 is the earliest and clearest report of the exact same non-persistent-buffer regression later restated in 44534, and its wording is broad enough to serve as the canonical issue for that duplicate pair.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44534 best captures the concrete, reproducible v5 buffer-initialization bug and is the broadest clear issue among the true duplicates here.", + "best_issue_reason": "Issue 43644 is the best issue to anchor the cluster because it is the cleanest exact duplicate target among the soft edges and represents a concrete, reproducible regression rather than a model-specific variant.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "Different features and failure modes: AudioFlamingo3 track leakage vs Whisper empty-transcription handling." + "reason": "Different models and different failure modes; both mention generation problems, but they do not describe the same underlying bug." }, { "left": "issue:44877", "right": "issue:45030", "accept": false, - "reason": "Both are config-loading regressions, but they affect different models and likely different validation paths." + "reason": "Both involve config/loading validation, but the affected models and reported failures are different and not a clear shared code-path bug." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Same model family, but the reported crashes are different (StopIteration vs mask shape mismatch) and do not look like one bug." + "reason": "Unrelated errors: a Qwen3-vl video StopIteration versus a tensor mask shape mismatch." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "Unrelated problems: Deepspeed/BertModel zero3 init vs add-new-model-like tokenizer mapping handling." + "reason": "One is a DeepSpeed/BertModel zero3 init crash; the other is a tokenizer-mapping limitation in add-new-model-like." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "Both involve loading/offload/memory, but the concrete symptoms and code paths differ." + "reason": "Different problems: dequantized model offload loading versus mmap OOM on Strix Halo." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Different subsystems and failures; no evidence of the same underlying bug." + "reason": "Different bug classes and code paths; one is zero3/BertModel indexing, the other is tokenizer mapping generation." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer-mapping edge case vs tensor mask shape mismatch; these are not the same bug." + "reason": "No shared underlying bug beyond both being errors; the model/config contexts are unrelated." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "Both mention SigLIP2, but one is zero probabilities and the other is docs/model-processor/quantization issues; too different to merge." + "reason": "Same model family, but one is bad probabilities and the other is a documentation example with multiple setup errors; not the same concrete bug." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "Near-identical reports of the same Transformers v5 non-persistent-buffer junk-initialization regression." + "reason": "Near-verbatim duplicate: both report Transformers v5 filling non-persistent buffers with junk." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "Different Qwen3.5 bugs: ZeRO-3 weight loading vs incorrect visual encoder keys on save_pretrained." + "reason": "Both concern Qwen3.5, but one is ZeRO-3 loading of language_model weights and the other is save_pretrained writing wrong visual encoder keys." }, { "left": "issue:45488", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but they hit different model families and different failure mechanisms." + "reason": "Both are tokenizer regressions, but they affect different model families and different concrete tokenizer behavior." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "Different models and different flash-attention generation failures." + "reason": "Different models and different failures; no shared bug is evident." }, { "left": "issue:44451", "right": "issue:44488", "accept": false, - "reason": "Both are model-loading failures, but the reports are too generic and model-specific to confidently treat as one bug." + "reason": "Both are model-loading complaints, but the titles do not identify the same underlying defect or code path." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Different loading regressions with different causes; shared mention of current branch/accelerate is not enough." + "reason": "Different subsystems: LoRA/qwen3_moe compatibility versus BitNet packed-weight handling." }, { "left": "issue:43854", "right": "issue:43931", "accept": false, - "reason": "Different models and different load errors; no shared concrete bug." + "reason": "Both are loading issues, but the reported model-specific failures are different and not clearly the same bug." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Both are Qwen3-related, but one is device-map/cuda assert and the other is FineGrainedFP8Config; distinct failures." + "reason": "Qwen3 auto device mapping cuda assert is not the same issue as FineGrainedFP8Config failure." }, { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Training schedule math vs optimizer argument handling are unrelated." + "reason": "Training schedule math versus optimizer argument handling; unrelated bugs." }, { "left": "issue:42491", "right": "issue:45276", "accept": false, - "reason": "Different topics: Qwen3 MoE LoRA loading vs embedding resize propagation." + "reason": "One is Qwen3 MoE LoRA compatibility; the other is resize_token_embeddings not propagating in Gemma4." }, { "left": "issue:43257", "right": "issue:43854", "accept": false, - "reason": "Different model-loading problems with no concrete shared code path." + "reason": "Qwen3 MoE weight conversion during accelerate+deepspeed is unrelated to GLM-4.7-Flash load failures." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Both mention memory/offload, but one is Qwen3 MoE training memory use and the other is quantization offloading behavior." + "reason": "Memory-usage complaint versus quantization/offloading behavior; too broad and not the same bug." }, { "left": "issue:42915", "right": "issue:44756", "accept": false, - "reason": "Distinct issues: Qwen3Moe FP8 config failure vs mmap/OOM on Strix Halo." + "reason": "Different failure domains: Qwen3Moe FP8 config versus mmap OOM on Strix Halo." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Different model families and different failure modes." + "reason": "Different Qwen3-family loading failures with different symptoms and code paths." }, { "left": "issue:39692", "right": "issue:43994", "accept": false, - "reason": "Same general model family, but the docs example errors and nonsensical outputs are not clearly the same underlying bug." + "reason": "Same model name, but the first is a docs-example error bundle while the second is an actual nonsensical-output regression; not clearly the same concrete bug." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both are memory-related, but the training-memory and int4 reserved-memory/OOM reports are different regressions." + "reason": "Both mention memory, but one is training inefficiency and the other is int4 quantization causing OOM; not the same issue." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "Notebook custom-model initialization is a different issue from the non-persistent-buffer junk regression." + "reason": "One is a buffer-initialization regression; the other is a custom-model notebook initialization issue." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Both are flash-attention crashes, but one is a packed-sequence/position_ids bug and the other is an s_aux=None attribute error." + "reason": "Both touch flash attention, but one is a Qwen3.5 packed-sequence misparse and the other is an AttributeError on sink-less models." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Unrelated model/runtime crashes in different components." - }, - { - "left": "issue:42491", - "right": "issue:45292", - "accept": false, - "reason": "LoRA loading on Qwen3 MoE is unrelated to resize_token_embeddings propagation." + "reason": "Different products and failures: chat crash on Qwen3.5-35B versus Gemma4Processor missing _tokenizer in serve." }, { "left": "issue:44488", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading complaints, but they concern different models and insufficiently specific root causes." + "reason": "Both are tokenizer-loading regressions, but they concern different models and no shared concrete defect is established." }, { "left": "issue:45276", "right": "issue:45335", - "accept": true, - "reason": "Both describe the same resize_token_embeddings bug: the resized vocabulary is not propagated to downstream embeddings/output layers in model-specific wrappers." + "accept": false, + "reason": "Similar API surface, but different model families and different affected submodules; too little evidence for one duplicate bug." }, { - "left": "issue:43404", - "right": "issue:43454", + "left": "issue:45313", + "right": "issue:45357", "accept": false, - "reason": "Both are untied lm_head reports, but they are different model families and not clearly the same code-path bug." + "reason": "Different Qwen3.5 regression families: ZeRO-3 weight loading versus visual-encoder key persistence." }, { - "left": "issue:44910", - "right": "issue:45588", + "left": "issue:43404", + "right": "issue:43454", "accept": false, - "reason": "Both involve flash attention, but the crash mechanisms are different and not mergeable as one fix." + "reason": "Both involve lm_head tying, but they are separate model classes and the titles do not establish the same concrete code-path defect." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The two accepted soft pairs are well supported by the titles and pair evidence, and the rejected pairs generally avoid overclaiming on broad subsystem similarity alone. The canonical/best-issue choice is also consistent with the buffer-regression cluster." + "feedback": "The assessment is grounded in the packet and stays conservative overall. The only accepted soft edge is well supported by the near-identical titles for issues 43644 and 44534, and the rejected pairs generally avoid overclaiming duplicate status when the packet only shows superficial similarity. Minor phrasing like \u201cexact same regression\u201d is a bit stronger than the evidence, but not enough to overturn the overall precision." }, "evaluator_used": true, "retried": false, @@ -1986,8 +1980,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -2350,8 +2344,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -2683,8 +2677,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -3039,8 +3033,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -3350,8 +3344,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -3679,8 +3673,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -3998,8 +3992,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -4320,8 +4314,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -4625,8 +4619,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -4930,8 +4924,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -5213,8 +5207,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -5525,8 +5519,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -5846,8 +5840,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -6129,8 +6123,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -6461,8 +6455,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -6794,8 +6788,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -7085,8 +7079,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -7417,8 +7411,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -7767,8 +7761,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -8072,8 +8066,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -8377,8 +8371,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -8678,8 +8672,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -8969,8 +8963,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -9288,8 +9282,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -9586,8 +9580,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -9905,8 +9899,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -10210,8 +10204,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -10507,8 +10501,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -10819,8 +10813,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -11145,8 +11139,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -11467,8 +11461,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -11814,8 +11808,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -12125,8 +12119,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -12465,8 +12459,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -12770,8 +12764,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -13131,8 +13125,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -13477,8 +13471,8 @@ "review_unit_count": 45, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ @@ -13893,7 +13887,7 @@ "issue:33453|issue:34689", "issue:42757|issue:43576" ], - "prepared_review_unit_hash": "23f9da61fc978a9e2fe4c2784fa93c4d07b685f3a875c6746bac11057cc2a7a0", + "prepared_review_unit_hash": "d920bfabba481c67ee8de9ecd9c6162b849002cb89b5c7c51623d5ce7f24c09d", "component_budget": { "node_count": 392, "item_count": 392, @@ -13915,36 +13909,36 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of superficially similar Transformers issues about loading/import regressions, but the concrete failures vary a lot (tokenizers, model configs, docs, flash attention, FP8, CI, etc.). I do not see any pair that clearly represents the same underlying bug/change.", - "confidence": 0.83, - "canonical_issue_reason": "issue:45278 is the broadest umbrella report here, covering multiple import failures after upgrading from 4.57.0 to 5.5.0 and thus best represents the general regression theme in the cluster.", + "summary": "This cluster is mostly a loose similarity set around Transformers v5 import/load regressions, but the individual issues are largely different bugs. No pull requests are present. 45278 is the best umbrella issue, though the cluster is too heterogeneous for a strong duplicate canon.", + "confidence": 0.82, + "canonical_issue_reason": "Issue 45278 is the broadest, most representative report: many import errors after upgrading to v5. It best matches the recurring upgrade-related import/load failure theme across the set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best single representative issue because it is wide in scope, user-facing, and aligned with the cluster\u2019s dominant v5 breakage pattern, while the other issues are narrower or unrelated specifics.", + "best_issue_reason": "45278 is the strongest global anchor because it is the most general and recent issue describing the dominant symptom family in this cluster. It is still only a partial fit since many items are unrelated specifics.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:28282", "right": "issue:33453", "accept": false, - "reason": "Both are loading/import problems, but one is a missing PyTorch dependency error and the other is a tokenizer loading regression; different root causes and fixes." + "reason": "Both are import/loading failures, but one is a missing-PyTorch ImportError and the other is a tokenizer-loading regression; different code paths." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "CLIP attentions being unset and an AMP float16 crash are different model/runtime failures, not the same bug." + "reason": "CLIPOutput attentions assignment and an AMP/CUDA crash in LwDetrImageLoss are unrelated bugs." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "One is about CLIPOutput attentions assignment; the other is Qwen3.5 generation with flash-attention. Different code paths and symptoms." + "reason": "Different symptoms and components: CLIPOutput attentions vs Qwen3.5 flash-attention generation." }, { "left": "issue:43618", "right": "issue:45588", "accept": false, - "reason": "CLIP attentions regression and flash_attention.py crashing on sink-less models are unrelated issues." + "reason": "AttributeError in flash_attention.py on s_aux=None is a different failure mode from CLIPOutput attentions not being assigned." }, { "left": "issue:44655", @@ -13956,187 +13950,163 @@ "left": "issue:43901", "right": "issue:44938", "accept": false, - "reason": "Docs mentioning return_all_scores is a documentation mismatch, not the Python 3.14 loading problem." + "reason": "Documentation mismatch for text-classification output is unrelated to Python 3.14 load failures." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "A flaky SamHQ integration test due to missing set_seed() is unrelated to Phi-4 multimodal model loading." + "reason": "A flaky SAM-HQ integration test is unrelated to model loading for Phi-4 multimodal." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "Test flakiness from missing seeds and a GraniteSpeech device override CI failure are different test failures." + "reason": "Both involve tests, but one is missing set_seed and the other is a stale device override CI failure; not the same bug." }, { "left": "issue:42890", "right": "issue:45600", "accept": false, - "reason": "SamHQ test seed flakiness and auto_mappings breaking CI due to removed configs are unrelated." + "reason": "Test nondeterminism and broken auto_mappings references are different issues." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "local_files_only still triggering API calls is a network/offline bug; AddedToken() argument duplication is a tokenizer constructor bug." + "reason": "local_files_only behavior and AddedToken keyword duplication are unrelated." }, { "left": "issue:43010", "right": "issue:44075", "accept": false, - "reason": "Cache update no_grad decoration and SGD optimizer args being ignored are unrelated code-path issues." + "reason": "Cache update no_grad decoration and unused SGD args are different code paths." }, { "left": "issue:42890", "right": "issue:45341", "accept": false, - "reason": "Both mention tests, but one is a seed-related integration test flake and the other is a specific bug in testing_utils.py." + "reason": "A missing set_seed in tests is not the same as a bug in testing_utils.py." }, { "left": "issue:42548", "right": "issue:44351", "accept": false, - "reason": "PreTrainedModel import failure and HybridCache import failure are distinct missing-symbol regressions." + "reason": "Both are import errors, but for different symbols and likely different export regressions." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "FP8 save_pretrained on moe and missing _tp_plan for tensor parallelism are different model export vs parallelism issues." + "reason": "FP8 save_pretrained behavior and missing tensor-parallel plan are separate problems." }, { "left": "issue:43502", "right": "issue:44485", "accept": false, - "reason": "Offline API-call leakage and GLM-5 RoPE implementation are unrelated." + "reason": "local_files_only API leakage is unrelated to GLM-5 RoPE implementation." }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Compiled Python file errors and slower filtering after upgrade are not the same failure." + "reason": "Compiled Python file errors and a performance regression after upgrade are not the same bug." }, { "left": "issue:45125", "right": "issue:45478", "accept": false, - "reason": "Missing tensor-parallel plan and Qwen3.5 MoE from_pretrained errors are related only by model family, not the same bug." + "reason": "Both touch Qwen3.5 MoE, but one is tensor-parallel metadata and the other is a from_pretrained regression; too different to merge." }, { "left": "issue:30990", "right": "issue:31795", "accept": false, - "reason": "Stuck loading sentence transformers and confusing forward docs are different categories entirely." + "reason": "Sentence Transformers getting stuck loading is unrelated to forward-signature documentation confusion." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Missing _tp_plan and a missing deepstack_visual_indexes field are different Qwen3.5 MoE issues." + "reason": "Missing tensor-parallel plan and a strict-config field drop are different model/config issues." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 quantization OOM from reserved memory growth and inability to reload checkpoints trained on v4.57 are not the same defect." + "reason": "Int4 memory/OOM behavior and checkpoint reload compatibility are different regressions." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "Decorator/no_grad concerns on cache updates and broad import errors after upgrade are different code paths." + "reason": "A no_grad decoration issue is unrelated to a general import-error report." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "MLFlow reporting on failed jobs and tokenizer loading regression are unrelated." + "reason": "MLFlow reporting on failed training jobs is unrelated to tokenizer loading regression." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "AutoTokenizer.from_pretrained v5 loading problem and checkpoint reload incompatibility are different failure modes." + "reason": "Tokenizer loading in v5 and checkpoint reload after upgrading are both load-related, but not the same concrete failure." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "Offline network calls and FP8 moe save_pretrained are unrelated." + "reason": "local_files_only network calls and FP8 save_pretrained bugs are unrelated." }, { "left": "issue:43010", "right": "issue:44368", "accept": false, - "reason": "cache update no_grad and tie_word_embeddings warning during LoRA fine-tuning are different issues." + "reason": "Cache update autograd decoration and a tie_word_embeddings warning are different issues." }, { "left": "issue:44315", - "right": "issue:44360", - "accept": false, - "reason": "Liger Kernel not applied with model_init and a DSA indexer missing ReLU are unrelated." - }, - { - "left": "issue:43010", "right": "issue:45850", "accept": false, - "reason": "Cache update decoration and a broad complaint that 5.0 breaks too many models are not the same concrete bug." - }, - { - "left": "issue:43502", - "right": "issue:44961", - "accept": false, - "reason": "Offline-file loading bug and a placeholder issue titled 'racoon' are not meaningfully comparable." - }, - { - "left": "issue:42831", - "right": "issue:43874", - "accept": false, - "reason": "FineGrainedFP8 accuracy issues and a missing image-patch-count method in GLM46V are different FP8/model bugs." - }, - { - "left": "issue:30333", - "right": "issue:36296", - "accept": false, - "reason": "Failed MLFlow reporting and tensor parallel training bug are unrelated training issues." + "reason": "Liger Kernel not applied with model_init is a specific integration bug, while 45850 is only a vague broad complaint." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Compiled Python file loading errors and PretrainedConfig type checking regressions are different problems." + "reason": "Compiled-file loading errors and PretrainedConfig type-checking regressions are not the same bug." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Compiled file errors and saving Pipeline objects are unrelated." + "reason": "Compiled Python file errors are unrelated to save_pretrained for pipelines." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "FP8 save_pretrained for moe and fp8 inference support for qwen3-vl/qwen3.5 are adjacent but not the same bug." + "reason": "FP8 save_pretrained for MoE and FP8 inference support for Qwen3.5 are related in area but not the same fixable code-path." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Docs still referencing pipeline() and an unrelated placeholder issue are not the same issue." + "reason": "Docs referencing pipeline() after removals and an unrelated placeholder issue are not duplicates." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Tokenizer loading regression and Llama 3.2 90B Vision model loading breakage are different regressions." + "reason": "Tokenizer loading regression and Llama 3.2 model loading breakage are different load failures." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "Missing is_offline_mode import and broken 'transformers env' command are separate v5 import/CLI problems, not one bug." + "reason": "Importing is_offline_mode and the broken transformers env command are unrelated." } ] }, @@ -14251,7 +14221,7 @@ "issue:44295|issue:45230", "issue:41669|issue:44351" ], - "prepared_review_unit_hash": "be4369d3a697b11073603a1fb4d302183c07fadea12d9e813d4cd0e982026e18", + "prepared_review_unit_hash": "13417d2242fc2cc2d1644ce8c4124387c52c4dd018136473e6178ee13f4a65e7", "component_budget": { "node_count": 392, "item_count": 392, @@ -14273,252 +14243,252 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is a loose collection of mostly unrelated issues, with several broad v5 regression/import reports but no clear duplicate pairs. I would not merge any of the soft candidates; they share subsystems at most, not the same concrete bug.", - "confidence": 0.73, - "canonical_issue_reason": "issue:45850 is the best umbrella-style issue in this set: it is broad, open, and explicitly about many model breakages after v5, so it is the most plausible dedupe anchor.", + "summary": "This cluster is mostly a grab-bag of unrelated Transformers issues, with a loose common thread of v5 regressions and import/load breakages. There is no defensible single duplicate target; the closest umbrella is the broad \"v5 breaks many models\" report, but it is too generic to canonicalize the whole set.", + "confidence": 0.18, + "canonical_issue_reason": "No safe canonical: the issues span unrelated bugs (docs, import errors, tokenizer/model loading, training/runtime failures), so they are not the same underlying defect.", "canonical_pr_reason": null, - "best_issue_reason": "Same choice; it is the only issue that reads like a catch-all report rather than a single narrow symptom.", + "best_issue_reason": "issue:45850 is the broadest umbrella for the shared v5-breakage theme, but it is too generic to serve as a true duplicate anchor.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Both are v5 model-loading regressions, but they target different model families and different failure contexts." + "reason": "Both involve model loading after v5, but one is Qwen3-VL MoE-specific and the other is general checkpoint reload incompatibility." }, { "left": "issue:43010", "right": "issue:45656", "accept": false, - "reason": "Cache/no_grad decoration and double optimizer stepping are different training-path bugs." + "reason": "Different problems: no_grad decoration for cache/layer updates versus DeepSpeed calling optimizer.step twice." }, { "left": "issue:33453", "right": "issue:36296", "accept": false, - "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated." + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated code paths." }, { "left": "issue:43576", "right": "issue:43824", "accept": false, - "reason": "Broken env command and missing Qwen2.5-VL export are separate issues." + "reason": "Broken env command is not the same as a missing exported class import." }, { "left": "issue:43576", "right": "issue:45071", "accept": false, - "reason": "An env command regression and a PretrainedConfig type-checking regression are not the same bug." + "reason": "v5 env command breakage and PretrainedConfig type-checking regression are different failures." }, { "left": "issue:44961", "right": "issue:45468", "accept": false, - "reason": "The titles are unrelated and point to different model/content areas." + "reason": "No relation beyond being separate model-specific bugs; titles do not indicate the same defect." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Documentation confusion for forward arguments is unrelated to an import error." + "reason": "Documentation confusion in model.forward is unrelated to an ImportError for layer_type_validation." }, { "left": "issue:41628", "right": "issue:42548", "accept": false, - "reason": "Both are top-level import failures, but for different symbols with no evidence of one shared root cause." + "reason": "Both are import errors, but for different symbols and likely different packaging regressions." }, { "left": "issue:38617", "right": "issue:43576", "accept": false, - "reason": "Missing configuration_utils symbol and broken env command are different problems." + "reason": "Specific import symbol breakage is not the same as the transformers env command being broken." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "A cache update autograd issue and a Python-version support issue are unrelated." + "reason": "Cache update no_grad issue and Python-version compatibility problem are unrelated." }, { "left": "issue:43576", "right": "issue:44351", "accept": false, - "reason": "Different missing/broken import paths; no clear single underlying code-path defect." + "reason": "Env command breakage and HybridCache import failure are different issues." }, { "left": "issue:44908", "right": "issue:44961", "accept": false, - "reason": "Scheduler kwargs handling and a nonsensical title are unrelated." + "reason": "Scheduler kwargs handling is unrelated to the racoon-named issue." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor-parallel training and TextClassificationPipeline docs are not the same bug." + "reason": "Training bug versus documentation mismatch; not the same bug." }, { "left": "issue:41628", "right": "issue:44355", "accept": false, - "reason": "Top-level import failure and compiled-file execution errors do not match." + "reason": "AutoImageProcessor import failure and compiled-file execution errors are different problems." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Training bug and BeitImageProcessorFast label reduction bug are different code paths." + "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are unrelated." }, { "left": "issue:44261", "right": "issue:44360", "accept": false, - "reason": "These are different numerical/model-component issues with no shared concrete defect." + "reason": "Precision/config issue in MLA q_a_layernorm is unrelated to the DSA indexer ReLU discussion." }, { "left": "issue:44273", "right": "issue:45003", "accept": false, - "reason": "Lazy loading failure and unsafe sys.modules access are related in theme but not clearly the same bug." + "reason": "Both touch lazy/import behavior, but one is a generic lazy-loading complaint and the other is unsafe sys.modules access." }, { "left": "issue:44273", "right": "issue:45542", "accept": false, - "reason": "Lazy loading and a missing TensorFlow backend guard are unrelated." + "reason": "Lazy loading breakage is not the same as the TensorFlow backend error from tensorboard-only installs." }, { "left": "issue:44623", "right": "issue:45230", "accept": false, - "reason": "A specific save_pretrained bug and a generic bug report title are not enough to establish duplication." + "reason": "Processor save_pretrained missing files is concrete; \"Bug report\" is too vague to match it." }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Both involve Qwen3 variants, but one is bbox output error and the other is an infinite loop on a specific image." + "reason": "Both are Qwen3-VL-related, but one is 2D box hallucination/error and the other is an infinite loop on a specific image." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "Broken env command and checkpoint reload incompatibility are different regression reports." + "reason": "Broken env command is not the same as checkpoint reload incompatibility after upgrade." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "A vision-model output bug and a config type-checking regression are unrelated." + "reason": "Qwen3-VL output bug and PretrainedConfig type-checking regression are different defects." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Qwen3-VL model loading and tensor-parallel plan support are different issues." + "reason": "Broad Qwen3-VL-Moe failure and missing _tp_plan for tensor parallelism are not the same code-path bug." }, { "left": "issue:43525", "right": "issue:45850", "accept": false, - "reason": "A missing pad_token_id attribute in one config is much narrower than the broad v5-breakage umbrella." + "reason": "Missing pad_token_id in Llama4Config is model-specific, not the broad v5-breakage meta issue." }, { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Import-* performance regression and generation cache missing during chunked prefill are different problems." + "reason": "Removing import * from models and chunked_prefill cache absence are unrelated." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both are upgrade/loading regressions, but they involve different model families and specific failure modes." + "reason": "Both concern old checkpoints after v5, but they affect different model families and different failure mechanisms." }, { "left": "issue:44373", "right": "issue:44961", "accept": false, - "reason": "Wrong docstring for position_ids and an unrelated title are not duplicates." + "reason": "Wrong position_ids docstring has no connection to the racoon issue." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "A specific StableLmConfig field regression is not the same as a broad 'many models break' report." + "reason": "StableLmConfig pad_token_idx regression is specific, not the broad v5-breakage umbrella." }, { "left": "issue:45362", "right": "issue:45850", "accept": false, - "reason": "A specific Qwen3.5 chat crash is too narrow to be the same issue as a generic v5 breakage umbrella." + "reason": "Qwen3.5 chat crash is a model-specific runtime bug, not the generic v5-wide complaint." }, { "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "Test seeding flakiness and scheduler kwargs handling are unrelated." + "reason": "Test flakiness from missing set_seed is unrelated to inverse_sqrt scheduler kwargs handling." }, { "left": "issue:44704", "right": "issue:44908", "accept": false, - "reason": "AutoProcessor cached_file kwargs forwarding and inverse_sqrt scheduler kwargs are different code paths." + "reason": "AutoProcessor kwargs forwarding and scheduler kwargs forwarding are different components and bugs." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Import slowdown and lazy-loading malfunction are related only broadly; no same underlying bug is shown." + "reason": "Import slowness and lazy loading not working are related at a high level but not clearly the same underlying bug." }, { "left": "issue:43408", "right": "issue:44315", "accept": false, - "reason": "A model-type warning and Liger Kernel not being applied are unrelated." + "reason": "Model type warning and Liger Kernel not applied with model_init are unrelated." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python support regression and Qwen3-VL bounding-box hallucination are not the same issue." + "reason": "Python-version compatibility issue is unrelated to the Qwen3-VL bounding-box bug." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Flash-Attention support warning and a vision output bug are unrelated." + "reason": "Flash Attention support limitation and Qwen3-VL bounding-box output error are different issues." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "Broken env command and scheduler kwargs handling are unrelated." + "reason": "Broken env command and scheduler kwargs handling do not share the same bug." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler parameter forwarding and PretrainedConfig type checking do not share a concrete bug." + "reason": "Scheduler timescale kwargs and PretrainedConfig type checking are unrelated." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "Tokenizer save_pretrained mismatch and a generic bug report title are not enough to infer duplication." + "reason": "Tokenizer config mismatch after save_pretrained is not the same as a generic bug report." }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "position_ids buffer access error and a generic bug report title are not enough to infer duplication." + "reason": "Buffer/position_ids reading error is a specific bug, while the other item is too vague to match it." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Both touch imports, but one is a performance cleanup and the other is a missing export/import error." + "reason": "Import-* cleanup in models and HybridCache import failure are unrelated." } ] }, @@ -14644,7 +14614,7 @@ "issue:31515|issue:33453", "issue:43298|issue:44230" ], - "prepared_review_unit_hash": "ed99a9b9ecb3d4bce0a2419324cd37a9084fbd01034a76c97c08cd9963b9c746", + "prepared_review_unit_hash": "244ee41145414b9c3fc768821af05ab88205ec7defb4e8d396d98354aa2e2ecd", "component_budget": { "node_count": 392, "item_count": 392, @@ -14666,318 +14636,294 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is noisy and mostly composed of unrelated issues that happen to mention Transformers v5 regressions, loading/import errors, or model-specific bugs. None of the soft edges are strong duplicates under a strict triage standard. Issue 45278 is the best umbrella representative for the cluster\u2019s dominant v5 import/model-loading regression theme.", - "confidence": 0.79, - "canonical_issue_reason": "45278 is the most concrete umbrella report: it describes broad import/model-loading failures after upgrading to v5.5.0 and is more actionable than the vaguer v5 complaints.", + "summary": "The cluster is noisy and only loosely connected by Transformers v5 regression reports around loading/import/model-init behavior. I do not see any soft pair that is a true duplicate, so all soft edges are rejected. The best umbrella issue is the broad v5 breakage/import-regression report.", + "confidence": 0.61, + "canonical_issue_reason": "issue:45278 is the best umbrella for the cluster: it is the broadest active report of v5 upgrade breakage and is more representative than the very vague catch-all issues.", "canonical_pr_reason": null, - "best_issue_reason": "45278 best represents the cluster because it captures the common post-v5 breakage theme without being too vague, unlike 45850.", + "best_issue_reason": "issue:45278 is the most actionable and central issue among the set, covering the common v5 regression theme better than the narrower model-specific bugs or generic placeholders.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43673", "right": "issue:44492", "accept": false, - "reason": "Different bugs: generation cache missing vs a typo in cache strategies." + "reason": "Different bug: chunked_prefill cache handling vs cache-strategy typo." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "Unrelated: import-star cleanup performance issue vs a testing_utils bug." + "reason": "Unrelated: import-star cleanup/perf vs testing_utils bug." }, { "left": "issue:45278", "right": "issue:45850", "accept": false, - "reason": "Both are broad v5 complaints, but one is a concrete import-error report and the other is too vague to be the same bug." + "reason": "Both are broad v5 complaints, but one is about import errors and the other is a generic breakage report; not the same concrete issue." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "Different model-specific issues: 2D bbox hallucination vs Qwen3.5 MoE from_pretrained error." + "reason": "Different model/problem: Qwen3-VL bbox output vs Qwen3.5 MoE from_pretrained error." }, { "left": "issue:43874", "right": "issue:45850", "accept": false, - "reason": "Specific multimodal processor API crash vs a generic v5 complaint; not the same defect." + "reason": "Specific GLM46V processor AttributeError vs a generic 'many models break' complaint." }, { "left": "issue:44315", "right": "issue:44829", "accept": false, - "reason": "Different code paths: model_init/Liger kernel application vs flash_attention_3 training degeneration." + "reason": "Liger Kernel application via model_init is unrelated to flash_attention_3 training degeneration." }, { "left": "issue:41669", "right": "issue:44492", "accept": false, - "reason": "Import-star refactor/perf issue is unrelated to a cache-strategy typo." + "reason": "Different issue: import-star cleanup vs cache-strategy typo." }, { "left": "issue:43827", "right": "issue:44908", "accept": false, - "reason": "Docs still referencing pipeline() is unrelated to the inverse_sqrt scheduler kwargs bug." + "reason": "Docs removal issue vs scheduler kwargs bug." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "Different failures: patchtsmixer post_init validation vs tied-weight key handling." + "reason": "Tied-weight key crash is unrelated to the optional post_init policy change." }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Documentation confusion about model.forward args is not the same as tokenizer loading regression." + "reason": "Docs confusion vs tokenizer-loading regression." }, { "left": "issue:41669", "right": "issue:44908", "accept": false, - "reason": "Import-star cleanup is unrelated to scheduler kwargs not being passed." + "reason": "Import-star cleanup vs scheduler kwargs bug." }, { "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "TF32 settings documentation issue is unrelated to a cache-strategy typo." + "reason": "TF32 settings migration vs cache-strategy typo." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Broken env command and lazy loading failure are different features and different bugs." + "reason": "Both are v5 regressions, but env CLI breakage and lazy-loading failure are distinct code paths." }, { "left": "issue:44655", "right": "issue:44861", "accept": false, - "reason": "Saving Pipeline objects and tied-weight key crashes are unrelated." + "reason": "Saving pipelines and tied-weight key handling are unrelated." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "DSA ReLU concern is unrelated to Gemma audio positional encoding." + "reason": "Different models/code paths: DSA ReLU vs Gemma-4 audio positional encoding." }, { "left": "issue:44492", "right": "issue:45850", "accept": false, - "reason": "A typo in cache strategies is not the same as a generic complaint that v5 breaks models." + "reason": "Cache-strategy typo vs a generic 'many models break' complaint." }, { "left": "issue:44273", "right": "issue:44908", "accept": false, - "reason": "Lazy loading failure and inverse_sqrt scheduler kwargs are unrelated." + "reason": "Lazy loading vs inverse_sqrt scheduler kwargs." }, { "left": "issue:45230", "right": "issue:45310", "accept": false, - "reason": "One is a generic bug report placeholder; the other is a specific Qwen3.5 MoE loading error." + "reason": "Generic bug report placeholder vs specific Qwen3.5 MoE from_pretrained failure." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Different model internals: Qwen3VL timestamp calculation vs GLM-5 RoPE implementation." + "reason": "Qwen3VL timestamp math vs GLM-5 RoPE implementation." }, { "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "Import-star usage cleanup is unrelated to a VRAM leak in Qwen3ForCausalLM." + "reason": "Import-star cleanup vs VRAM leak." }, { "left": "issue:43519", "right": "issue:44908", "accept": false, - "reason": "Timestamp calculation bug and scheduler kwargs bug are unrelated." + "reason": "Timestamp calculation vs scheduler kwargs." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Doc wording confusion is not the same as a Llama 3.2 model-loading regression." + "reason": "Docs confusion vs model-loading regression." }, { "left": "issue:31795", "right": "issue:37428", "accept": false, - "reason": "Model.forward docs issue is unrelated to the missing flash-attention import error." + "reason": "Docs confusion vs ImportError in configuration_utils." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Liger/model_init application and old remote-code checkpoint meta-init incompatibility are different bugs." + "reason": "Liger Kernel/model_init issue vs remote-code/meta-init incompatibility." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leak in Qwen3ForCausalLM is unrelated to GLM-5 RoPE implementation." + "reason": "VRAM leak vs GLM-5 RoPE implementation." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "Different models and different subsystems: RoPE vs audio positional encoding." + "reason": "Different models and bugs: GLM-5 RoPE vs Gemma-4 audio encoding." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 API guidance is unrelated to a VRAM leak." + "reason": "TF32 settings vs VRAM leak." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "local_files_only network requests and timestamp calculation are unrelated." + "reason": "local_files_only being ignored is unrelated to timestamp calculation." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Timestamp math and missing files on save_pretrained are different issues." + "reason": "Timestamp math vs processor.save_pretrained file output." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Qwen3VL timestamp calculation and VRAM leakage are unrelated." - }, - { - "left": "issue:44263", - "right": "issue:45468", - "accept": false, - "reason": "torch.split return values issue is unrelated to Gemma audio positional encoding." - }, - { - "left": "issue:43606", - "right": "issue:45468", - "accept": false, - "reason": "CPU offload device mismatch is unrelated to audio positional encoding." - }, - { - "left": "issue:44261", - "right": "issue:45468", - "accept": false, - "reason": "MLA rms_norm_eps precision mismatch is unrelated to Gemma audio positional encoding." - }, - { - "left": "issue:43704", - "right": "issue:45341", - "accept": false, - "reason": "VRAM leak bug is unrelated to a testing_utils issue." + "reason": "Timestamp math vs VRAM leak." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both mention tokenizer v5 changes, but one is a broad behavior change and the other a specific decoder-type mismatch; not clearly the same defect." + "reason": "Related tokenizer-v5 theme, but behavior drift and decoder-type bug are different concrete issues." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Scheduler kwargs bug is unrelated to the placeholder unemployment issue." + "reason": "Scheduler kwargs bug vs an irrelevant placeholder issue." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "Tied-weight key crash and chat-template tool-call crash are different code paths." + "reason": "Tied-weight key crash vs apply_chat_template crash." }, { "left": "issue:43704", "right": "issue:44998", "accept": false, - "reason": "VRAM leak bug is unrelated to the placeholder unemployment issue." + "reason": "VRAM leak vs an irrelevant placeholder issue." }, { "left": "issue:41669", "right": "issue:44998", "accept": false, - "reason": "Import-star cleanup issue is unrelated to the placeholder unemployment issue." + "reason": "Import-star cleanup vs an irrelevant placeholder issue." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_id in Llama4Config is unrelated to tied-weight key handling." - }, - { - "left": "issue:43066", - "right": "issue:44998", - "accept": false, - "reason": "Tokenizer decoder-type bug is unrelated to the placeholder unemployment issue." + "reason": "pad_token_id/config regression vs tied-weight key crash." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is unrelated to tied-weight key crashes." + "reason": "pad_token_idx/config regression vs tied-weight key crash." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Slow from_pretrained checkpoint loading and a missing import name are unrelated." + "reason": "Slow checkpoint loading vs missing import symbol." }, { "left": "issue:44360", "right": "issue:44998", "accept": false, - "reason": "DSA indexer ReLU concern is unrelated to the placeholder unemployment issue." + "reason": "DSA ReLU issue vs an irrelevant placeholder issue." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 support request is unrelated to missing processor files on save_pretrained." + "reason": "fp8 support request vs processor.save_pretrained file bug." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLflow reporting after failed training and slow checkpoint loading are unrelated." + "reason": "MLflow run-state reporting vs checkpoint-loading slowdown." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Slow checkpoint loading and tensor-parallel training bug are different problems." + "reason": "Checkpoint loading slowdown vs tensor-parallel training bug." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Checkpoint loading speed issue is unrelated to model.forward doc confusion." + "reason": "Checkpoint loading slowdown vs docs typo." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "FP8 inference support request is unrelated to a Qwen3.5 MoE from_pretrained error." + "reason": "fp8 inference support vs from_pretrained error." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Slow from_pretrained checkpoint loading is unrelated to tokenizer loading regression." + "reason": "Checkpoint loading slowdown vs tokenizer-loading regression." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return issue vs Gemma-4 audio encoding." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching not supporting audio models is unrelated to FP8 inference support." + "reason": "Audio continuous batching support vs fp8 Qwen3.5/Qwen3-VL support." } ] }, @@ -14996,8 +14942,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-26350-2", "nodes": [ @@ -15059,8 +15005,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-27088-4", "nodes": [ @@ -15159,8 +15105,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-36817-15", "nodes": [ @@ -15473,8 +15419,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-37934-6", "nodes": [ @@ -15589,8 +15535,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-41084-2", "nodes": [ @@ -15652,8 +15598,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43598-2", "nodes": [ @@ -15715,8 +15661,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43684-2", "nodes": [ @@ -15778,8 +15724,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43835-4", "nodes": [ @@ -15878,8 +15824,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-44371-5", "nodes": [ @@ -16000,8 +15946,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45145-2", "nodes": [ @@ -16120,8 +16066,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45672-2", "nodes": [ @@ -16183,8 +16129,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45762-2", "nodes": [ @@ -16246,8 +16192,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45764-2", "nodes": [ @@ -16330,8 +16276,8 @@ ], "soft_pairs": [ "pull_request:39895|pull_request:43424", - "pull_request:41855|pull_request:43823", "pull_request:41855|pull_request:43424", + "pull_request:41855|pull_request:43823", "pull_request:42668|pull_request:43823", "pull_request:43251|pull_request:43823", "pull_request:43251|pull_request:44827", @@ -16349,154 +16295,154 @@ "pull_request:43823|pull_request:45795", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "4285980add19684098a6eb3132da3a02a9a9ba5364f5062529421d70e35f1f3e", + "prepared_review_unit_hash": "0d29c97773f93d624dfca062d790de1cff5692ca75dfb035a9a5b2230e5fd66e", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 19, - "serialized_chars": 35196, - "estimated_input_tokens": 8799, - "estimated_eval_tokens": 17854 + "serialized_chars": 35204, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 19, - "serialized_chars": 35196, - "estimated_input_tokens": 8799, - "estimated_eval_tokens": 17854 + "serialized_chars": 35204, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The set is mostly a grab bag of unrelated PRs across models, docs, tests, and utility refactors. Only the two loss-utils PRs (43251 and 43254) look like true duplicates of the same cross-entropy kwargs fix.", - "confidence": 0.96, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the clearest canonical representative for the duplicated loss-utils fix: it directly updates `fixed_cross_entropy` to pass supported kwargs into `nn.functional.cross_entropy` and is tied to the tracking issue. PR 43254 is a narrower rephrasing of the same code-path change.", - "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the best overall PR candidate because it is the most complete and explicit implementation of the shared bug fix, with a direct issue link and the same concrete code-path change as 43254.", + "summary": "This cluster is mostly unrelated PRs. The only true duplicate pair is the two `fixed_cross_entropy` changes (PRs 43251 and 43254), which target the same underlying loss-function fix for issue 43240. Everything else is a different model, docs, or test-only change and should stay separate.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 43240 is the shared underlying bug for the loss-function changes; both 43251 and 43254 are fixing that same `fixed_cross_entropy` kwargs handling.", + "canonical_pr_reason": "PR 43254 is the cleaner canonical representative: it directly adds supported kwargs to `fixed_cross_entropy` with the same code-path fix, while 43251 is a near-identical variant tied to the same issue.", + "best_issue_reason": "If an issue must be chosen for this cluster, 43240 is the only clear canonical issue because it is the explicit target of the duplicate loss-fix PRs.", + "best_pr_reason": "PR 43254 is the best global representative of the duplicate pair because it is the more straightforward implementation of the same `cross_entropy` kwargs support change.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Different domains: VideoPrism model addition vs. ExecuTorch export dynamic-shape test. No shared bug or mergeable code change." + "reason": "Unrelated PRs: VideoPrism model addition vs Executorch dynamic-shape test only." }, { "left": "pull_request:41855", - "right": "pull_request:43823", + "right": "pull_request:43424", "accept": false, - "reason": "Mistral tokenizer helper methods vs. adding MobileLLM model support. Unrelated changes." + "reason": "Different changes: Mistral tokenizer utility methods vs Executorch export test coverage." }, { "left": "pull_request:41855", - "right": "pull_request:43424", + "right": "pull_request:43823", "accept": false, - "reason": "Tokenizer API additions and an ExecuTorch test are unrelated and do not fix the same underlying problem." + "reason": "Tokenizer method fix is unrelated to adding the MobileLLM model." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-loading robustness changes vs. adding a new model. Same broad area of model support, but not the same concrete bug." + "reason": "Processor auto-creation robustness work is unrelated to MobileLLM model addition." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Cross-entropy loss kwargs fix and MobileLLM model addition are unrelated." + "reason": "Loss-function kwargs fix is unrelated to MobileLLM model implementation." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Loss utility kwargs plumbing vs. Mistral4 test/model fixes; different code paths and problems." + "reason": "Different code paths: loss utility kwargs support vs Mistral4 test/model fixes." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "ExecuTorch dynamic-shape test and Mistral4 test fixes target different systems." + "reason": "Executorch test coverage and Mistral4 fixes are distinct changes." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "ExecuTorch export test vs. new model support. No shared underlying bug." + "reason": "Executorch export tests do not match a new model implementation." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "New model implementation vs. config-resolution order fix. Completely different changes." + "reason": "MobileLLM model addition and config-resolution fix are unrelated." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "MobileLLM model addition and Falcon output-interface refactor are unrelated." + "reason": "New MobileLLM model addition is unrelated to Falcon output-interface refactoring." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon refactor and Mistral4 test fix affect different models and different issues." + "reason": "Falcon refactor and Mistral4 test/model fixes address different models and code paths." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon model refactor vs. repository-wide model-creation skill; not the same code-path change." + "reason": "Falcon model refactor is unrelated to the model-creation skill PR." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 tests/integrations fix vs. CLIP-like `layrnorm` renaming cleanup; unrelated." + "reason": "Mistral4 test fixes and layrnorm/layernorm renaming are different bugs/changes." }, { "left": "pull_request:44827", "right": "pull_request:45795", "accept": false, - "reason": "Mistral4 test fixes and docs for audio/video processors do not address the same bug or feature." + "reason": "Mistral4 fixes are unrelated to docs for audio/video processing components." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Model-specific Mistral4 test work vs. config resolution order in `modeling_utils.py`; unrelated." + "reason": "Mistral4 test/model fixes are unrelated to config-resolution ordering." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Mistral4 tests vs. a draft model-creation skill scaffold are not the same change." + "reason": "A model-specific test fix is not the same as the model-creation skill PR." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "Adding MobileLLM support is unrelated to adding a model-creation skill and docs." + "reason": "MobileLLM model addition and the skill docs/model scaffolding PR are not the same change." }, { "left": "pull_request:43823", "right": "pull_request:45795", "accept": false, - "reason": "MobileLLM model code and docs for audio/video processors are different repository features." + "reason": "MobileLLM model addition is unrelated to docs for adding audio/video processors." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs patch `fixed_cross_entropy` in the same way: plumbing supported kwargs to `nn.functional.cross_entropy`. They are near-duplicate fixes for the same concrete bug and could plausibly be merged as one PR." + "reason": "Both PRs implement the same concrete `fixed_cross_entropy` kwargs support fix in the same file and are plausible duplicates for issue 43240." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft-edge pair, 43251/43254, is well supported by the shared filename and shared issue target, and the rest are reasonably treated as unrelated or at least not the same concrete bugfix. I don\u2019t see an overstatement that would warrant rejection." + "feedback": "The cluster summary is well grounded in the packet: the only pair with explicit shared-issue evidence is PRs 43251 and 43254, and they are mergeable as the same `fixed_cross_entropy` kwargs bugfix for issue 43240. The other pairwise judgments stay conservative and are supported by the diff previews (distinct models, docs, or tests)." }, "evaluator_used": true, "retried": false, @@ -16523,7 +16469,7 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "9299a110dfb22004b99c755f0114cc88dc4fc24ca8511cc44cbc556ef2d0db2a", + "prepared_review_unit_hash": "8fd7a67a7b28d6ef54332d00878a69d875f366a2c18e18cb601f2744337c7603", "component_budget": { "node_count": 2, "item_count": 2, @@ -16545,18 +16491,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs overlap on the VibeVoice family, but they are not duplicates: one implements the base model, the other adds the realtime variant and related tokenizer/generation pieces.", - "confidence": 0.88, + "summary": "Both PRs are about VibeVoice, but they are not the same change: #40546 implements the base VibeVoice integration, while #42781 adds a separate realtime variant plus an acoustic tokenizer. Shared auto/model files reflect the same subsystem, not a duplicate code change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #40546 is the core VibeVoice implementation and appears more mature/reviewed; PR #42781 is a separate realtime extension rather than the same change.", + "canonical_pr_reason": "#40546 is the broader, earlier base implementation of VibeVoice and is the more canonical PR for the main model integration; #42781 is a later, narrower realtime follow-up.", "best_issue_reason": null, - "best_pr_reason": "PR #40546 is the strongest single representative of the cluster because it targets the base model implementation and has substantial review activity, while #42781 is a draft extension.", + "best_pr_reason": "#40546 is the best PR representative because it covers the core VibeVoice addition end-to-end and is not a draft, whereas #42781 is a draft PR for a distinct realtime extension.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Different scope and code change: 'Implement VibeVoice' vs 'Add VibeVoice Realtime'. The second PR adds realtime-specific support and acoustic tokenizer work, so they are not the same concrete fix/change and would not plausibly be merged as one PR." + "reason": "They share the VibeVoice subsystem and some files, but the PRs target different concrete changes: base VibeVoice integration vs. realtime/acoustic-tokenizer extension. Not a single mergeable duplicate fix." } ] }, @@ -16586,12 +16532,12 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "8202cbb704d5d8049b6805241660fb4d823ccb08cb92f039b791d2d763ab6da3", + "prepared_review_unit_hash": "441c42788a8270edf914d627337a297c391c773df12b803e0ea8918868b538e4", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4674, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -16599,7 +16545,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4674, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -16608,18 +16554,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are unrelated: one adds covariate-based forecasting support for TimesFM, the other adds DINOv3 image-classification support. They do not fix the same code path or represent the same change.", - "confidence": 0.99, + "summary": "The two PRs are unrelated feature additions in different model families and code paths: TimesFM covariate forecasting vs. DINOv3 image classification support. They should not be clustered as duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No true canonical PR for this cluster; if forced, #41224 is the cleaner standalone feature PR, but it is not a duplicate of #40755.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "#41224 is the better standalone PR: it is focused, has a clear API addition, and shows more review activity. #40755 is a separate, unrelated feature area.", + "best_pr_reason": "Neither PR is a good canonical representative for a duplicate set because there is no shared underlying bug/change; if forced, the cluster has no valid PR anchor.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different models and different functionality: TimesFM covariate forecasting versus DINOv3 image classification. They do not share the same underlying bug or change and could not plausibly be merged into one PR." + "reason": "Different models, different tasks, and different code paths; one adds TimesFM covariate forecasting while the other adds DINOv3 image classification support." } ] }, @@ -16714,12 +16660,12 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "d00618cb833b500279edac13d3ce8dd2b7293cb6830c50a7e4eeec8f24467f8b", + "prepared_review_unit_hash": "089332678d6166adc99f0bdfc8e87ff4486446c1a616fc53a9d03e43ac093365", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10428, + "serialized_chars": 10427, "estimated_input_tokens": 2607, "estimated_eval_tokens": 5470 }, @@ -16727,7 +16673,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10428, + "serialized_chars": 10427, "estimated_input_tokens": 2607, "estimated_eval_tokens": 5470 }, @@ -16736,24 +16682,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three unrelated pull requests adding support for different models (DeepSeek OCR, Isaac, and Kimi2-6). They share framework boilerplate and auto-registration files, but not the same underlying bug or change.", - "confidence": 0.97, + "summary": "These PRs are separate model-addition efforts (DeepSeek OCR, Isaac, and Kimi2-6), sharing only generic Transformers integration boilerplate. They are not duplicates of the same underlying change.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: the items are separate model-addition PRs for different models and do not represent one duplicate change.", + "canonical_pr_reason": "No canonical PR: each pull request adds a different model with distinct files, configs, and implementation details.", "best_issue_reason": null, - "best_pr_reason": "No single PR is a good cluster representative because the PRs target different model integrations rather than one shared fix or feature.", + "best_pr_reason": "No single PR is a good representative duplicate target because the PRs do not fix the same code path or implement the same model.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Both are model-addition PRs, but for different models (DeepSeek OCR vs Isaac). Shared registration/docs scaffolding is not enough to treat them as the same change." + "reason": "Different models and different integrations: DeepSeek OCR vs Isaac. Shared scaffold files are just normal model-registration boilerplate." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "They add different models (Isaac vs Kimi2-6) and touch shared transformer plumbing only as part of separate integrations, not one mergeable fix." + "reason": "Different model additions: Isaac vs Kimi2-6. They touch similar auto-mapping areas but implement unrelated changes." } ] }, @@ -16783,7 +16729,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "8e36c6824715235e1423b1dc913722c50e29b28e4fc76ffa52110040a0e4c913", + "prepared_review_unit_hash": "8b1299124250ef038da9be352b2f7e3a3c1f8f8666eded607573f7f867568f5b", "component_budget": { "node_count": 2, "item_count": 2, @@ -16805,18 +16751,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two workflow-maintenance PRs with overlapping GitHub Actions files, but they upgrade different action families and target different concerns; not duplicates.", - "confidence": 0.95, + "summary": "Two open PRs both update GitHub Actions workflow dependencies, but they target different upgrade tracks and different action families. They are related by maintenance theme only, not the same fix/change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the cleaner canonical representative: it has the more specific problem statement (Node 24 compatibility) and a broad set of workflow-action version bumps.", + "canonical_pr_reason": "PR #42975 is the better representative because it is the more specific, theme-defining change: upgrading workflow actions for Node 24 compatibility across many workflows.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the best single representative of the cluster because its scope and motivation are explicit, while PR 42976 is a separate general update focused on newer versions.", + "best_pr_reason": "PR #42975 is the best PR candidate overall since it clearly states the compatibility goal and covers the broader set of workflow action version bumps tied to that goal.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "They are both GitHub Actions upgrade PRs, but the concrete changes differ: 42975 updates checkout/cache/upload-artifact and related workflow actions for Node 24 compatibility, while 42976 bumps docker/build-push-action and a different set of workflow actions to latest versions. Shared workflow filenames alone are not enough to treat them as the same underlying change." + "reason": "Different underlying changes: #42975 upgrades actions like checkout/cache/upload-artifact for Node 24 compatibility, while #42976 upgrades docker/build-push-action and a few other workflow actions to latest versions. They share workflow maintenance context but not the same concrete bug or mergeable change." } ] }, @@ -16859,88 +16805,88 @@ "pull_request:44601|pull_request:45838", "pull_request:45490|pull_request:45838" ], - "prepared_review_unit_hash": "eac57268e2d9d84a5b8f5c3b38668ef7837009afaf26db235acb2cb3183f704a", + "prepared_review_unit_hash": "e58d8ee4363bc81b9732f44f6fee2e8d82d975e9f5cc1413491375fe82da092e", "component_budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23513, - "estimated_input_tokens": 5879, - "estimated_eval_tokens": 12014 + "serialized_chars": 23511, + "estimated_input_tokens": 5878, + "estimated_eval_tokens": 12012 }, "budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23513, - "estimated_input_tokens": 5879, - "estimated_eval_tokens": 12014 + "serialized_chars": 23511, + "estimated_input_tokens": 5878, + "estimated_eval_tokens": 12012 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "No true duplicate pairs here: the PRs are separate model additions or an unrelated distributed-loading change, with only superficial overlap in boilerplate docs/auto-registration files.", - "confidence": 0.95, + "summary": "These PRs are not duplicates: they cover separate model additions (ViT NEPA, Molmo, Molmo2, Lfm2 Audio, CTSM, PP-OCRv6) plus one distributed loading feature. Shared files are mostly boilerplate registry/docs updates, not the same underlying change.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43451 is the strongest standalone candidate to keep: it is the most mature and comprehensive model-addition PR in this set, with extensive implementation, processor/image/video support, tests, and the highest discussion activity; the others are different changes.", + "canonical_pr_reason": "No true duplicate PR exists in this cluster. The items are independent feature PRs across different models or subsystems, so none is a canonical duplicate target.", "best_issue_reason": null, - "best_pr_reason": "PR 43451 is the best representative PR overall because it is the most complete and reviewed change in the group, while the other PRs are clearly separate features rather than the same fix or model add.", + "best_pr_reason": "PR 45838 is the strongest standalone representative only in the sense that it is a complete model-support PR with concrete implementation and tests. It is still not a duplicate of the others, but it is the most self-contained among the set.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Both are model-addition PRs, but they add different models (ViT NEPA vs Molmo) with different codepaths and targets; shared docs/auto files are just boilerplate." + "reason": "Different model families (ViT NEPA vs Molmo). Overlap is limited to docs/auto-registration boilerplate, not the same code-path bug or change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "ViT NEPA and Molmo2 are distinct model families with different implementations and tests; overlap is only in registration/docs scaffolding." + "reason": "Different models (ViT NEPA vs Molmo2). Same generic model-addition pattern, but not the same implementation." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA and CTSM are unrelated model additions; no same underlying bug or change." + "reason": "Different models (ViT NEPA vs CTSM). Shared auto/docs edits are incidental." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are different model releases with separate model/processor stacks; not the same concrete change." + "reason": "Molmo and Molmo2 are distinct model integrations with different filenames and behaviors; not the same underlying change." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo and CTSM are unrelated model additions; shared auto/model registry edits do not make them duplicates." + "reason": "Molmo vs CTSM are unrelated model additions." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are separate model implementations with different architectures and files; not mergeable as one PR." + "reason": "Molmo2 vs CTSM are unrelated model additions." }, { "left": "pull_request:43973", "right": "pull_request:45838", "accept": false, - "reason": "Lfm2 audio support and PP-OCRv6 text recognition are different domains and codepaths; the overlap is only generic model-addition boilerplate." + "reason": "Lfm2 Audio and PP-OCRv6 text recognition are different modalities and different model implementations." }, { "left": "pull_request:44601", "right": "pull_request:45838", "accept": false, - "reason": "Pipeline-parallel loading support is an infrastructure change, while PP-OCRv6 is a model-family addition; they do not fix the same problem." + "reason": "One is pipeline-parallel loading support; the other is model support for PP-OCRv6. Different subsystem and different change." }, { "left": "pull_request:45490", "right": "pull_request:45838", "accept": false, - "reason": "CTSM and PP-OCRv6 are different model additions with different implementations, tests, and documentation; not duplicates." + "reason": "CTSM and PP-OCRv6 text recognition are different model additions, not mergeable as one fix." } ] }, @@ -16973,12 +16919,12 @@ "pull_request:43291|pull_request:44815", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "4014f1af4925a56cc392ba522c70a122c03bec943bd7d21808539319dc2e63bf", + "prepared_review_unit_hash": "05078b5f0ebfd4b7a0f0442028c9256abd073b292d5dcbfea248d21340ff68d5", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7092, + "serialized_chars": 7090, "estimated_input_tokens": 1773, "estimated_eval_tokens": 3802 }, @@ -16986,7 +16932,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7092, + "serialized_chars": 7090, "estimated_input_tokens": 1773, "estimated_eval_tokens": 3802 }, @@ -16995,30 +16941,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "No pair looks like the same underlying PR/change. The cluster mixes an unrelated Whisper tokenizer fix, a test-only CLIP/ViT PR, and a substantive FP8 dequant/model-loading fix. PR 44815 is the strongest standalone change, but it is not a duplicate of the others.", + "summary": "These PRs do not look like duplicates: one is a Whisper decode/tokenization fix, one is a test-only CLIP/ViT PR with unrelated assertions, and one is a broader FP8 dequantization/loading fix for Mistral. The only similarity is generic \"fix\" wording.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44815 is the most substantive and concrete code fix in the set, with a clear bugfix path in model loading / fine-grained FP8 integration. The other PRs are unrelated or test-only.", + "canonical_pr_reason": "PR 44815 is the most substantial and representative change set in the cluster, with a concrete code-path fix spanning model loading and FP8 dequantization rather than a narrow model-specific tweak or test-only edit.", "best_issue_reason": null, - "best_pr_reason": "PR 44815 is the best representative because it fixes a specific runtime/code-path issue and has a meaningful implementation diff, unlike the test-only or unrelated Whisper PRs.", + "best_pr_reason": "PR 44815 is the strongest candidate to keep as the cluster representative because it contains the clearest, multi-file functional fix and is the least obviously incidental of the three.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Whisper tokenizer decode logic vs CLIP/ViT test edits; different subsystems and different kinds of changes, so not the same bug or patch." + "reason": "Whisper tokenizer decoding vs. CLIP/ViT test assertions; different models, different code paths, and the second PR appears test-only and unrelated." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper timestamp decoding fix is unrelated to FP8 dequant/model-loading changes; no shared concrete code path." + "reason": "Whisper decode logic and FP8 dequant/model-loading changes are unrelated bugs in different subsystems; no shared concrete fix path." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "Test-only CLIP/ViT PR does not match the FP8/core loading bugfix; they could not plausibly be merged as one duplicate change." + "reason": "A test-only CLIP/ViT PR does not match a Mistral FP8 dequantization fix; they do not appear to address the same underlying change or bug." } ] }, @@ -17048,12 +16994,12 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "40f0a6496ddcde9980b4f95c4ca2ecf6c78a53667f6312b9befc45cc67001e25", + "prepared_review_unit_hash": "254d39ac4469588b5b02cca2ecc509fb5fc0dc6ee5cab41a2d96b1c13b0ac415", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4562, + "serialized_chars": 4563, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17061,7 +17007,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4562, + "serialized_chars": 4563, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17070,18 +17016,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are not duplicates: one is a small repo-bot/setup formatting check, while the other makes broader CI/workflow and testing changes. Shared Vit test edits are incidental and not enough to unify them.", - "confidence": 0.9, + "summary": "The two PRs are not duplicates: #43488 is a small repo-bot/versioning test change, while #43532 is a larger workflow/CI diff-display change. They only share a test filename and do not appear to fix the same underlying code-path problem.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43532 is the better representative of the cluster because it contains the substantive workflow/testing changes; PR 43488 is a tiny synthetic \"don't merge\" repo-bot check and does not capture the same change set.", + "canonical_pr_reason": "If one PR must serve as the cluster representative, #43532 is the better canonical choice because it is the broader, more coherent CI/workflow change; #43488 is a separate narrow repo-bot/version bump test PR.", "best_issue_reason": null, - "best_pr_reason": "PR 43532 is the strongest standalone PR in the set: it touches multiple CI/workflow files plus test utilities, whereas PR 43488 is a narrow setup/version tweak meant for bot-checking rather than representing the cluster.", + "best_pr_reason": "#43532 is the stronger representative PR because it has the larger, clearer change set and a more substantive end-to-end purpose than #43488.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Different underlying changes and code paths: 43488 is a setup/version/repo-bot formatting test, while 43532 changes CI workflows, notification logic, and test utilities. The shared Vit test file is not enough to treat them as the same PR." + "reason": "Different purposes and code paths: #43488 touches setup/versioning and a ViT test for a repo-bot check, while #43532 rewires CI/comment workflows and related utilities. Shared test filename alone is not enough to treat them as the same change." } ] }, @@ -17111,7 +17057,7 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "cec91b7dffd3300698ae4385fc67d99a23f05c85bbcc2433d04dc1988817c31a", + "prepared_review_unit_hash": "b685725e55f10d1132e569131698e94f64699464d637259e335f90f00985077c", "component_budget": { "node_count": 2, "item_count": 2, @@ -17133,18 +17079,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs share pipeline/docs infrastructure, but they implement different features: Promptable Concept Segmentation vs Promptable Visual Segmentation, with different model and test coverage. They are related in theme, not the same underlying change.", + "summary": "These are two separate feature PRs: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share framework/docs scaffolding, but they target different tasks and model integrations, so they should not be deduplicated.", "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: these are separate pipeline additions for different segmentation tasks and should not be merged as duplicates.", + "canonical_pr_reason": "No canonical PR: 43612 and 43613 are different pipeline features with different task names and model/test coverage, not the same underlying change.", "best_issue_reason": null, - "best_pr_reason": "Neither PR is a global best representative of the other; each targets a distinct feature area and code path.", + "best_pr_reason": "If one PR must represent the cluster, 43613 is slightly broader, but it is still a distinct feature from 43612 and should not subsume it.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Different pipelines/features with different model and test files; shared docs and infrastructure are not enough to treat them as the same change." + "reason": "Different underlying features: concept segmentation vs visual segmentation. Shared scaffolding is expected, but the pipeline code, docs, and model/test targets are not the same change." } ] }, @@ -17174,12 +17120,12 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "2b74cf837e6a9180198cd641a8ab1d4d766fcb2591dd2fdcbf8997ffed1f5a84", + "prepared_review_unit_hash": "cdac7247e34a1762717068b04d54689416b99cf4852cc08511e3e5ffe0f00eac", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4291, + "serialized_chars": 4292, "estimated_input_tokens": 1073, "estimated_eval_tokens": 2402 }, @@ -17187,7 +17133,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4291, + "serialized_chars": 4292, "estimated_input_tokens": 1073, "estimated_eval_tokens": 2402 }, @@ -17196,18 +17142,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs touch `src/transformers/trainer.py` and add overridable trainer hooks, but they solve different problems: one changes gradient-accumulation loss scaling, the other changes input-signature/column filtering. They are related in theme but not duplicates.", - "confidence": 0.95, + "summary": "Two separate trainer extensibility PRs in the same file, but they change different behaviors: gradient-accumulation loss scaling vs signature-column filtering. They are not duplicates and should stay separate.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43651 is the better representative of the cluster because it changes the core training-step loss-scaling path; PR 43663 is a separate refactor for signature-column handling.", + "canonical_pr_reason": "No single canonical PR: PR #43651 adds a loss-scaling hook/property, while PR #43663 adds a signature-column helper for a different customization path.", "best_issue_reason": null, - "best_pr_reason": "PR 43651 is the stronger standalone candidate: it addresses a concrete training behavior change and adds a focused hook that custom trainers can use to control loss scaling.", + "best_pr_reason": "PR #43651 is the cleaner representative only in the sense that it is more self-contained, but it does not subsume PR #43663; the PRs solve different problems.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Not the same underlying change. 43651 adds `_loss_is_scaled_for_ga` to control gradient-accumulation loss normalization, while 43663 adds `_get_signature_columns` to control column filtering. Same file and extensibility theme, but different code paths and merge intents." + "reason": "Same file and same subsystem, but different concrete code paths and different extension points: one changes GA loss normalization, the other changes column filtering based on model signatures. They are not mergeable as one duplicate PR." } ] }, @@ -17239,7 +17185,7 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "0b062511e6c4bee14f4c2d56c7ca0f9680401ade583a898afc6a46e7e2e92998", + "prepared_review_unit_hash": "3e068c4c3985878850eef0b92546e20a9811673d8a9e657cb10fee73c9317406", "component_budget": { "node_count": 3, "item_count": 3, @@ -17261,34 +17207,34 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three PRs touch `src/transformers/cli/serve.py` and are related to typing/import-time annotation issues, but only PR 43842 cleanly targets the specific `TypeAdapter`/`pydantic` NameError. PR 43656 is a broader `__future__.annotations` and annotation-cleanup change, and PR 43836 is a wider Serve refactor; neither is conservative enough to treat as the same concrete fix as 43842.", - "confidence": 0.8, + "summary": "These are three open PRs against the same CLI serve module, but only 43836 and 43842 look like alternate fixes for the same TypeAdapter annotation NameError path. PR 43656 appears to address a different annotation/runtime typing issue and is not a true duplicate of the others.", + "confidence": 0.73, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43842 is the most precise, minimal fix: it explicitly imports `TypeAdapter` under `TYPE_CHECKING` and quotes the annotation at the use site to avoid the runtime NameError.", + "canonical_pr_reason": "PR 43842 is the most focused fix: it directly addresses the TypeAdapter NameError when pydantic is absent with a minimal TYPE_CHECKING import plus quoted annotation, making it the cleanest representative of this bug.", "best_issue_reason": null, - "best_pr_reason": "PR 43842 is the best representative because it directly addresses the concrete failure mode with the narrowest change set and least unrelated annotation churn.", + "best_pr_reason": "PR 43842 is the best standalone PR candidate because it targets the concrete failure mode most precisely and with the smallest change surface.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Both are in `serve.py`, but 43656 is a broader annotation cleanup (`__future__.annotations`, unquoting other types) while 43842 is a targeted `TypeAdapter` import/type-checking fix; they are related, but not the same mergeable bugfix." + "reason": "Both touch the same file and mention TypeAdapter, but 43656 looks like a broader typing/annotation cleanup while 43842 specifically fixes the pydantic-missing TypeAdapter import path. They do not read as the same concrete bug fix." }, { "left": "pull_request:43836", "right": "pull_request:43842", - "accept": false, - "reason": "43836 is a larger Serve refactor that happens to mention `TypeAdapter`, but it is not clearly the same concrete `pydantic` import-time NameError fix as 43842." + "accept": true, + "reason": "Both are alternate fixes for the same underlying TypeAdapter NameError in cli/serve.py, using different annotation-handling approaches. They could plausibly be merged into one PR." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The summary is a bit too strong on PR 43656 vs 43842. The packet only shows they share `serve.py` and a generic NameError/theme similarity; 43656 appears to be a broader `__future__.annotations`/annotation cleanup, while 43842 is specifically about importing `TypeAdapter` under `TYPE_CHECKING`. That is not enough to confidently call them the same concrete bugfix or a single mergeable PR. The rejection of 43836 vs 43842 is grounded, but the accepted pair is not conservative enough." + "accept": true, + "feedback": "The summary stays within the packet evidence: 43836 and 43842 both plausibly fix the same TypeAdapter annotation runtime issue in the same file, while 43656 is more broadly about annotation handling and has a different issue target. The soft-edge verdicts are conservative enough, and I do not see an overstatement that would warrant rejection." }, "evaluator_used": true, - "retried": true, - "accepted_nontrivial_soft_edge": false, + "retried": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -17408,8 +17354,8 @@ "pull_request:44066|pull_request:44072", "pull_request:44013|pull_request:44044", "pull_request:44066|pull_request:44086", - "pull_request:44066|pull_request:44071", "pull_request:44018|pull_request:44068", + "pull_request:44066|pull_request:44071", "pull_request:44066|pull_request:44068", "pull_request:44018|pull_request:44066", "pull_request:44019|pull_request:44722", @@ -17423,8 +17369,8 @@ "pull_request:44071|pull_request:44722", "pull_request:44018|pull_request:44086", "pull_request:44018|pull_request:44085", - "pull_request:44071|pull_request:44085", "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", "pull_request:44059|pull_request:44086", "pull_request:44085|pull_request:44086", "pull_request:44059|pull_request:44722", @@ -17439,9 +17385,9 @@ "pull_request:44017|pull_request:44071", "pull_request:44073|pull_request:44101", "pull_request:44059|pull_request:44071", + "pull_request:44073|pull_request:44161", "pull_request:44059|pull_request:44068", "pull_request:44056|pull_request:44101", - "pull_request:44073|pull_request:44161", "pull_request:44018|pull_request:44059", "pull_request:44101|pull_request:44161", "pull_request:43997|pull_request:44017", @@ -17473,430 +17419,352 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "e74478f6ffe85fbc82cd9787c8ed9db9af2036bf6940989818d32278fb3a2aa4", + "prepared_review_unit_hash": "8c4b258c17b89778c8e82cb31b3ca7065e040ec77a28df3f9b44d66b00632b6b", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84895, - "estimated_input_tokens": 21224, - "estimated_eval_tokens": 42704 + "serialized_chars": 84902, + "estimated_input_tokens": 21226, + "estimated_eval_tokens": 42708 }, "budget": { "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75092, - "estimated_input_tokens": 18773, - "estimated_eval_tokens": 37802 + "serialized_chars": 75098, + "estimated_input_tokens": 18775, + "estimated_eval_tokens": 37806 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of model-specific refactors to a standardized output-tracing API. Most PRs are not true duplicates because they touch different model families/code paths. The only clear duplicate groups are the GPT-Neo pair and the GPT-J/CodeGen pair(s).", - "confidence": 0.77, + "summary": "This cluster is mostly a set of model-specific refactors toward the same standardized output-tracing pattern, not one true duplicate set. I\u2019d only merge soft edges when the two PRs touch the same model/code path (not just the same meta issue #43979).", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44722 is the clearest canonical PR among the true duplicates: it is a later, broader GPT-J/CodeGen output-tracing refactor with the same concrete decorator migration and explicit issue linkage.", + "canonical_pr_reason": "PR 44722 is the best representative of the GPTJ/CodeGen duplicate subset: it covers the shared GPTJ tracing change, also updates CodeGen, and is explicitly tied to #43979.", "best_issue_reason": null, - "best_pr_reason": "PR 44722 is the best representative of the actual duplicated work: it captures the GPT-J output-tracing refactor cleanly and subsumes the related GPT-J/CodeGen changes.", + "best_pr_reason": "44722 is the broadest clean example of the standardized output-tracing refactor among these PRs, with the clearest same-code-path overlap and the most complete scope.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Both are output-tracing refactors, but they target different model families and different code paths." + "reason": "Different model families/files; same issue target alone does not make these duplicates." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different models and implementations; only the shared umbrella refactor theme overlaps." + "reason": "Different model families/files; these are separate refactors under the same umbrella issue." }, { "left": "pull_request:44066", "right": "pull_request:44085", - "accept": false, - "reason": "Same GPT-J area, but the previews suggest different refactor versions rather than one identical change set." + "accept": true, + "reason": "Same GPTJ tracing change in the same file; 44066 looks like the broader sibling/superset." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "Different model families; same standardized-output theme is too broad to count as a duplicate." + "reason": "RegNet and EfficientNet are different model-specific changes." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet vs GPT-J/CodeGen are unrelated code paths." + "reason": "Different model families/files; both are output-tracing refactors, but not the same change." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "Different model families and separate files; not the same underlying fix." + "reason": "Different model families/files; same refactor theme is not enough." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa are unrelated implementations despite similar API migration goals." + "reason": "Different model families/files; separate model-specific updates." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen refactor versus MGP-STR; no shared concrete bug or code path." - }, - { - "left": "pull_request:44066", - "right": "pull_request:44071", - "accept": false, - "reason": "GPT-J/CodeGen and MPT are distinct model refactors, not duplicates." + "reason": "GPTJ/CodeGen vs MGP-STR are unrelated concrete code paths." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Same GPT-Neo model family, same output-tracing migration, and overlapping files/tests indicate the same concrete refactor." + "reason": "Same GPT-Neo file and same output-tracing refactor; these look like duplicate/superset versions." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "Different model families/files; not the same underlying change." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen versus GPT-Neo; only the high-level decorator migration is shared." + "reason": "GPTJ/CodeGen and GPT-Neo are different model-specific changes." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "Different model families and code paths; not the same underlying change." + "reason": "Different model families/files; only the meta refactor pattern is shared." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet refactor is unrelated to GPT-J/CodeGen." + "reason": "ResNet and GPTJ/CodeGen are unrelated code paths." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are unrelated model implementations." + "reason": "Different model families/files; not the same concrete bug or change." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet and GPT-J are unrelated; same umbrella issue target does not make them duplicates." + "reason": "Different model families/files; same issue target is too broad." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and ResNet are separate model families with different refactors." + "reason": "GPT-Neo and ResNet are separate model-specific refactors." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet and MPT are different code paths." + "reason": "Different model families/files; no concrete overlap beyond the umbrella refactor." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert are unrelated implementations." + "reason": "GPT-Neo and Flaubert are different model-specific changes." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different model families." + "reason": "Different model families/files; same refactor theme is not enough." }, { "left": "pull_request:44018", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert are unrelated changes." + "reason": "GPT-Neo and Flaubert are unrelated concrete code paths." }, { - "left": "pull_request:44071", + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are different model-specific refactors." + }, + { + "left": "pull_request:44017", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J/CodeGen do not share the same concrete fix." + "reason": "Different model families/files; not the same underlying change." }, { - "left": "pull_request:44018", - "right": "pull_request:44086", + "left": "pull_request:44017", + "right": "pull_request:44073", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated model refactors." + "reason": "Segformer and VisualBert are separate model-specific updates." }, { - "left": "pull_request:44018", - "right": "pull_request:44085", + "left": "pull_request:44068", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and GPT-J are different code paths." + "reason": "GPT-Neo and MPT are different model families/files." }, { "left": "pull_request:44071", - "right": "pull_request:44086", + "right": "pull_request:44722", "accept": false, - "reason": "MPT and MGP-STR are unrelated; only the refactor pattern matches." + "reason": "Different model families/files; same meta issue is not enough." }, { "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT-2 and MGP-STR are unrelated model implementations." + "reason": "GPT2 and MGP-STR are unrelated concrete code paths." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J and MGP-STR are unrelated changes." + "reason": "Different model families/files; not the same bug/change." }, { "left": "pull_request:44059", "right": "pull_request:44722", "accept": false, - "reason": "GPT-2 refactor versus GPT-J/CodeGen refactor; different concrete code paths." + "reason": "GPT2 and GPTJ/CodeGen are separate model-specific refactors." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT and Flaubert are separate models with no shared fix." + "reason": "ViLT and XLM/Flaubert are different model-specific changes." }, { "left": "pull_request:44018", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and MPT are unrelated implementations." - }, - { - "left": "pull_request:44017", - "right": "pull_request:44161", - "accept": false, - "reason": "SegFormer and LongT5 are unrelated model families." - }, - { - "left": "pull_request:44017", - "right": "pull_request:44073", - "accept": false, - "reason": "SegFormer and VisualBert are separate code paths." - }, - { - "left": "pull_request:44068", - "right": "pull_request:44071", - "accept": false, - "reason": "GPT-Neo and MPT are different models; same broad API migration is not enough." - }, - { - "left": "pull_request:44071", - "right": "pull_request:44076", - "accept": false, - "reason": "MPT and ImageGPT are unrelated changes." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44073", - "accept": false, - "reason": "RegNet and VisualBert are different model families." - }, - { - "left": "pull_request:44017", - "right": "pull_request:44071", - "accept": false, - "reason": "SegFormer and MPT are unrelated code paths." - }, - { - "left": "pull_request:44073", - "right": "pull_request:44101", - "accept": false, - "reason": "VisualBert and Flaubert are unrelated implementations." - }, - { - "left": "pull_request:44059", - "right": "pull_request:44071", - "accept": false, - "reason": "GPT-2 and MPT are not the same underlying bug or refactor." - }, - { - "left": "pull_request:44056", - "right": "pull_request:44101", - "accept": false, - "reason": "MPNet and Flaubert are unrelated model changes." - }, - { - "left": "pull_request:44073", - "right": "pull_request:44161", - "accept": false, - "reason": "VisualBert and LongT5 are unrelated code paths." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44018", - "accept": false, - "reason": "RegNet and GPT-Neo are different model families." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44056", - "accept": false, - "reason": "RegNet and MPNet are unrelated refactors." - }, - { - "left": "pull_request:44071", - "right": "pull_request:44076", - "accept": false, - "reason": "MPT and ImageGPT are unrelated." + "reason": "GPT-Neo and MPT are unrelated concrete code paths." }, { "left": "pull_request:44074", "right": "pull_request:44101", "accept": false, - "reason": "TextNet and Flaubert are unrelated model implementations." + "reason": "TextNet and XLM/Flaubert are separate model-specific refactors." }, { "left": "pull_request:44056", "right": "pull_request:44161", "accept": false, - "reason": "MPNet and LongT5 are different code paths." + "reason": "MPNet and LongT5 are different model families/files." }, { "left": "pull_request:43997", "right": "pull_request:44018", "accept": false, - "reason": "RegNet and GPT-Neo are unrelated models." + "reason": "RegNet and GPT-Neo are different model-specific updates." }, { "left": "pull_request:43997", "right": "pull_request:44161", "accept": false, - "reason": "RegNet and LongT5 are unrelated." + "reason": "RegNet and LongT5 are unrelated code paths." }, { "left": "pull_request:44071", "right": "pull_request:44129", "accept": false, - "reason": "MPT and SpeechT5 are separate model families." - }, - { - "left": "pull_request:43996", - "right": "pull_request:44161", - "accept": false, - "reason": "CVT and LongT5 are unrelated refactors." + "reason": "MPT and SpeechT5 are different model-specific refactors." }, { "left": "pull_request:43996", "right": "pull_request:44017", "accept": false, - "reason": "CVT and SegFormer are different model families." + "reason": "CVT/FNet and Segformer are different model families/files." }, { "left": "pull_request:44010", "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBERT and MPT are unrelated changes." + "reason": "SqueezeBert and MPT are unrelated concrete changes." }, { "left": "pull_request:44010", "right": "pull_request:44073", "accept": false, - "reason": "SqueezeBERT and VisualBert do not share the same concrete fix." + "reason": "SqueezeBert and VisualBert are different model-specific refactors." }, { - "left": "pull_request:44018", - "right": "pull_request:44129", + "left": "pull_request:44017", + "right": "pull_request:44161", "accept": false, - "reason": "GPT-Neo and SpeechT5 are unrelated code paths." + "reason": "Segformer and LongT5 are separate model-specific changes." }, { - "left": "pull_request:43997", - "right": "pull_request:44074", + "left": "pull_request:44073", + "right": "pull_request:44101", "accept": false, - "reason": "RegNet and TextNet are unrelated model refactors." + "reason": "VisualBert and XLM/Flaubert are different model families/files." }, { - "left": "pull_request:43997", - "right": "pull_request:44129", + "left": "pull_request:44056", + "right": "pull_request:44161", "accept": false, - "reason": "RegNet and SpeechT5 are unrelated implementations." + "reason": "MPNet and LongT5 are unrelated concrete code paths." }, { - "left": "pull_request:44071", - "right": "pull_request:44129", + "left": "pull_request:43997", + "right": "pull_request:44018", "accept": false, - "reason": "MPT and SpeechT5 are different model families." + "reason": "RegNet and GPT-Neo are different model-specific refactors." }, { - "left": "pull_request:43996", + "left": "pull_request:43997", "right": "pull_request:44074", "accept": false, - "reason": "CVT and TextNet are unrelated model-specific refactors." + "reason": "RegNet and TextNet are separate model-specific changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet and Segformer are different model families/files." }, { "left": "pull_request:44010", "right": "pull_request:44044", "accept": false, - "reason": "SqueezeBERT and DeBERTa are separate code paths." + "reason": "SqueezeBert and DeBERTa v2 are unrelated concrete code paths." }, { "left": "pull_request:44044", "right": "pull_request:44074", "accept": false, - "reason": "DeBERTa and TextNet are unrelated model families." + "reason": "DeBERTa v2 and TextNet are different model-specific refactors." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Same GPT-J/CodeGen output-tracing refactor and same concrete decorator migration; 44722 looks like the broader later version of the same change." + "reason": "Same GPTJ/CodeGen output-tracing refactor; 44722 appears to be the later consolidated version." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Both touch GPT-J output tracing in the same file and replace the same legacy return path with standardized decorators; 44722 subsumes the GPT-J portion." + "reason": "Same GPTJ tracing change in the same file; these could plausibly be merged into one PR." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J and SpeechT5 are unrelated; the shared issue target is just an umbrella refactor label." - }, - { - "left": "pull_request:43996", - "right": "pull_request:44007", - "accept": false, - "reason": "CVT/FNet versus ResNet/RT-DETR-ResNet are unrelated model refactors." + "reason": "GPTJ and SpeechT5 are different model families/files." }, { "left": "pull_request:43996", "right": "pull_request:44129", "accept": false, - "reason": "CVT and SpeechT5 are unrelated code paths." + "reason": "CVT/FNet and SpeechT5 are unrelated concrete changes." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa and SpeechT5 are separate model families." + "reason": "DeBERTa v2 and SpeechT5 are different model-specific refactors." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa and Vits are unrelated model implementations." + "reason": "DeBERTa v2 and Vits are unrelated code paths." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative: it only treats the GPT-Neo pair and the GPT-J/CodeGen cluster as clear duplicates, which matches the deterministic accept pairs. The canonical/best-PR reasoning is also supported by the packet details for PR 44722. No soft-edge verdict appears to overstate the evidence." + "feedback": "Grounded overall: the packet supports a cluster of related output-tracing refactors rather than one universal duplicate set, and the accepted soft edges are limited to same-file/same-code-path overlaps that look mergeable into one PR. The summary is conservative about the umbrella issue link, and the chosen canonical PR (44722) is well-supported as the best GPTJ/CodeGen representative." }, "evaluator_used": true, "retried": false, @@ -17934,70 +17802,70 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "a9f3c614e6cb30919622da93f9c1d1e1fe0b7ef7cc5ff19f603d41d9d071a4ed", + "prepared_review_unit_hash": "bace331eb310592fe97c2291a946334fca8b4ccb479dde69ceec4ea7ca1379c4", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84895, - "estimated_input_tokens": 21224, - "estimated_eval_tokens": 42704 + "serialized_chars": 84902, + "estimated_input_tokens": 21226, + "estimated_eval_tokens": 42708 }, "budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17124, - "estimated_input_tokens": 4281, - "estimated_eval_tokens": 8818 + "serialized_chars": 17125, + "estimated_input_tokens": 4282, + "estimated_eval_tokens": 8820 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs form a loose theme of per-model migration to standardized output tracing, but they are not duplicates of the same underlying fix. Each one targets a different model/file and changes a different code path, so the soft edges should be rejected under strict PR deduping.", - "confidence": 0.96, + "summary": "These are model-specific PRs that all modernize output tracing / standardized output capture, but they target different architectures and code paths. They are thematically similar, not duplicates or mergeable into one PR.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "There is no true canonical duplicate PR here; if one representative is needed, PR 44073 is the clearest exemplar of the shared refactor theme because it explicitly wires `_can_record_outputs` and `capture_outputs` in a single model-specific migration.", + "canonical_pr_reason": "PR 44073 is a clear representative of the cluster: it has a concise title, touches the new standardized output-capture pattern directly, and the diff shows the core refactor (`capture_outputs`, `can_return_tuple`, `_can_record_outputs`) in a single model implementation.", "best_issue_reason": null, - "best_pr_reason": "PR 44073 is the best representative artifact for the cluster\u2019s theme, but only as a topic exemplar: it is a focused, well-scoped output-tracing migration with clear model-specific changes. It is not a duplicate of the others.", + "best_pr_reason": "PR 44073 is the best global exemplar because it most clearly expresses the common pattern across the cluster while remaining narrowly scoped to one model and one output-tracing refactor.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Both are standardized output-tracing refactors, but they touch different models and different execution paths (FocalNet vs ImageGPT). Similar migration pattern is not enough to treat them as the same change." + "reason": "Different models (FocalNet vs ImageGPT) and different implementations; same broad refactor theme, but not the same concrete bug or change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "VisualBert and TextNet are separate model implementations with distinct forward paths. These are parallel refactors, not one concrete bug fix that could be merged into a single PR." + "reason": "VisualBert and TextNet are unrelated code paths; both adopt standardized output tracing, but these are separate model refactors and not one mergeable change." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "MPNet and VisualBert each introduce model-specific output-capture wiring. They share a refactor style, but not the same underlying code-path problem." + "reason": "MPNet vs VisualBert, with model-specific output-hook wiring; similar pattern, but not the same underlying change." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "MPNet and TextNet are unrelated model code paths. The overlap is only the generic standardized-output migration pattern, which is too broad for duplicate PR treatment." + "reason": "MPNet and TextNet changes are independent model migrations to the same infrastructure, not a shared bug fix or duplicate PR." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert change different model internals. They are not the same fix; they just both adopt the new output-capture decorators." + "reason": "RegNet and SqueezeBert are different models with separate forward/output refactors; too broad to treat as the same PR." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and SpeechT5 are separate model-specific refactors. The shared theme is output tracing, but the concrete code paths and changes differ." + "reason": "SqueezeBert and SpeechT5 target different architectures and output-signature changes; similar tooling migration, but not the same concrete code-path problem." } ] }, @@ -18077,274 +17945,274 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "895d3659c51d21b153d756ff0c109bbc2ed2bd43b9621d45097fdf1cdba63995", + "prepared_review_unit_hash": "76571a9a9def5f8c3b1ce38534c5947b4453a10d72790e97389ab66de19b9a98", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40171, - "estimated_input_tokens": 10043, - "estimated_eval_tokens": 20342 + "serialized_chars": 40167, + "estimated_input_tokens": 10042, + "estimated_eval_tokens": 20340 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40171, - "estimated_input_tokens": 10043, - "estimated_eval_tokens": 20342 + "serialized_chars": 40167, + "estimated_input_tokens": 10042, + "estimated_eval_tokens": 20340 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs share a broad \"refactor output tracing\" theme, but they target different model families and concrete forward paths, so they should not be treated as duplicates. The best anchor for the cluster is the broader mamba/falcon_mamba refactor.", - "confidence": 0.83, + "summary": "This cluster is a set of parallel, model-specific refactors to adopt output-tracing / `can_return_tuple` patterns. They share a broad theme but do not appear to be duplicate fixes for the same concrete code path, so all soft edges are rejected.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44003 is the most representative anchor: it spans two closely related modules and introduces the output-capturing plumbing, making it the broadest concrete example of this refactor pattern.", + "canonical_pr_reason": "PR 44003 is the strongest representative of the cluster: it is a substantive output-tracing refactor across two closely related model files and introduces the shared capture/recording machinery, making it the most central example of the pattern.", "best_issue_reason": null, - "best_pr_reason": "PR 44003 is the strongest standalone representative because it makes the most substantial tracing change across related codepaths, while the others are narrower model-specific variants.", + "best_pr_reason": "PR 44003 is the best single anchor because it is broader and more infrastructure-like than the one-off model cleanups, while still clearly representing the cluster\u2019s core output-tracing refactor theme.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and different forward codepaths; same maintenance theme, not the same change." + "reason": "Different model families (`timm_backbone` vs `upernet`) and different forward/output code paths; same refactor theme, not the same change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Unrelated architectures with separate output-handling logic; not one concrete bug or fix." + "reason": "`timm_backbone` and `vision_text_dual_encoder` are unrelated model paths; both refactor output handling but not the same bug or fix." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Both are tracing refactors, but they modify different models and codepaths." + "reason": "Separate model implementations with no shared concrete code path; only a generic output-tracing similarity." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Timm backbone vs mamba/falcon_mamba are distinct implementations; no shared concrete fix." + "reason": "`timm_backbone` and `mamba/falcon_mamba` use different architectures and forward logic; not mergeable as one PR." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Separate model-specific refactors; too broad to count as the same underlying change." + "reason": "`timm_backbone` and `rwkv` are unrelated models; shared wording about output tracing is too broad to be a duplicate." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "Different model implementations and output plumbing; not mergeable as one PR." + "reason": "`mobilenet_v1` and `univnet` are different model code paths with different output objects; not the same underlying fix." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "MobileNetV1 and UperNet have unrelated forward paths despite similar refactoring style." + "reason": "Different models and different output plumbing; both are refactors, not duplicate fixes." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Distinct model families; similar refactor pattern does not make this the same change." + "reason": "`mobilenet_v1` vs `depth_anything` are separate model-specific refactors with no shared concrete defect." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different codepaths and modules; no shared concrete bug or fix." + "reason": "These touch unrelated encoder/decoder and image backbone code paths; similarity is only at the abstraction level." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "These are unrelated encoder/decoder refactors, not the same underlying issue." + "reason": "Different subsystems and output contracts; not the same underlying change." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Vision-text dual encoder and UnivNet are separate models with different output semantics." + "reason": "`vision_text_dual_encoder` and `univnet` are unrelated model implementations; same refactor pattern, different changes." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different architectures and forward signatures; only the refactor theme is shared." + "reason": "Different architecture and output signatures; no evidence they fix the same code-path issue." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Separate model families and distinct tracing plumbing; not the same code-path problem." + "reason": "`vision_text_dual_encoder` and `mamba/falcon_mamba` are distinct model families with no shared failing path." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "These target unrelated models, so they cannot be one duplicate change." + "reason": "Separate model families and forward methods; only a generic output-tracing overlap." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet vs UperNet are unrelated; similar output-tracing cleanup only." + "reason": "`univnet` and `upernet` are unrelated; no shared concrete bug or mergeable combined fix." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different model families and different forward behavior; not the same fix." + "reason": "Different model stacks and different output-capture mechanics; not duplicates." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Separate model-specific tracing refactors, not one concrete change." + "reason": "`univnet` and `depth_anything` are separate model-specific refactors, not the same bugfix." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "UperNet and RWKV are unrelated codepaths with different output handling." + "reason": "`upernet` and `rwkv` are unrelated code paths; same high-level theme only." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Different models and plumbing; no common underlying bug." + "reason": "`upernet` and `mamba/falcon_mamba` change different model implementations and cannot plausibly be one PR." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Mamba/falcon_mamba vs SuperPoint are unrelated implementations; similar refactor style only." + "reason": "`mamba/falcon_mamba` and `superpoint` are unrelated models with different output APIs; not the same fix." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "CodeGen cache/output signature cleanup is a different concrete change than mamba tracing refactors." + "reason": "`mamba/falcon_mamba` and `codegen` modify different forward paths and output conventions; not duplicate PRs." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen address different model internals and different API adjustments." + "reason": "`timm_backbone` and `codegen` are unrelated model implementations; similarity is only that both touch output handling." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "UnivNet and CodeGen are separate models; not the same underlying fix." + "reason": "Different architectures and output contracts; no shared concrete bug/change." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "Different architectures and output contracts; too broad to merge as one PR." + "reason": "`upernet` and `codegen` are unrelated subsystems; not mergeable as one PR." }, { "left": "pull_request:44000", "right": "pull_request:44004", "accept": false, - "reason": "Vision-text dual encoder and CodeGen are unrelated codepaths." + "reason": "`vision_text_dual_encoder` and `codegen` have different forward signatures and output paths; too broad to duplicate." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Depth-Anything and Vision-Encoder-Decoder are different model families; same refactor theme only." + "reason": "Both are output-tracing refactors, but for different model families (`depth_anything` vs `vision_encoder_decoder`) and different code paths." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "These are separate model-specific output tracing refactors, not one concrete bug fix." + "reason": "`depth_anything` and `speech_encoder_decoder` are separate model-specific changes, not the same underlying issue." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Depth-Anything and SuperPoint have unrelated forward paths and output logic." + "reason": "Different models and different output contracts; only a thematic overlap." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Different model families; no shared codepath or merged fix opportunity." + "reason": "`depth_anything` and `rwkv` refactor distinct implementations; no shared concrete bug." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Depth-Anything and DPR are unrelated implementations despite both touching tracing." + "reason": "`depth_anything` and `dpr` are different model families with different output plumbing." }, { "left": "pull_request:44026", "right": "pull_request:44029", "accept": false, - "reason": "Vision-Encoder-Decoder and RWKV are unrelated; not the same underlying change." + "reason": "`vision_encoder_decoder` and `rwkv` are unrelated code paths; same refactor theme only." }, { "left": "pull_request:44026", "right": "pull_request:44027", "accept": false, - "reason": "Different encoder/decoder stacks and different tracing adjustments." + "reason": "Different encoder-decoder stacks and output handling; not the same change." }, { "left": "pull_request:44026", "right": "pull_request:44028", "accept": false, - "reason": "Separate models with different output contracts; not a duplicate." + "reason": "`vision_encoder_decoder` and `superpoint` are separate model implementations with no shared failure mode." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Vision-Encoder-Decoder and DPR are unrelated codepaths." + "reason": "Different model families and different forward/output logic; not duplicate PRs." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech-Encoder-Decoder and SuperPoint are unrelated model families." + "reason": "`speech_encoder_decoder` and `superpoint` are unrelated; output-tracing similarity is too broad." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Different models and output plumbing; only the general refactor theme matches." + "reason": "`speech_encoder_decoder` and `rwkv` touch distinct model paths and output semantics." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Speech-Encoder-Decoder and DPR are separate codepaths with different fixes." + "reason": "Different architectures and output contracts; not the same underlying change." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are unrelated implementations, so this is not the same change." + "reason": "`superpoint` and `rwkv` are unrelated models with different forward behavior." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Different model families and output semantics; not mergeable into one PR." + "reason": "`superpoint` and `dpr` do not share the same concrete code path or bug." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR are unrelated model-specific refactors, not a shared concrete fix." + "reason": "`rwkv` and `dpr` are separate model implementations; same general refactor pattern, not a duplicate fix." } ] }, @@ -18377,7 +18245,7 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "f7c0301a5f440dc25e48eff6d8b8ea974a7eead802a0f64ec19e63d94ad58798", + "prepared_review_unit_hash": "edb556165b2e3c6b50ae9d14866add3f843b53adb72d82b352748caff6c54fb7", "component_budget": { "node_count": 3, "item_count": 3, @@ -18399,30 +18267,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three pull requests are separate model additions (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share generic Transformers integration files, but they do not fix the same bug or implement the same model/change, so none should be deduplicated together.", + "summary": "These are three separate model-addition PRs (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share repository plumbing patterns, but they are not the same underlying change and should not be deduplicated.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: these are distinct model-support additions for different architectures and use cases, with only broad framework-registration overlap.", + "canonical_pr_reason": "No true canonical PR for a duplicate cluster here; the PRs implement different models. If one must be picked as the most representative, #45075 is the most anchored because it has an explicit issue target and a fuller, self-contained model integration, but it is still not a duplicate of the others.", "best_issue_reason": null, - "best_pr_reason": "No single PR is a better duplicate representative than the others because they are unrelated changes rather than variants of the same fix.", + "best_pr_reason": "#45075 is the most complete and structured of the three, with an explicit linked issue and broad integration work, but it should only be treated as a representative PR, not as the same change as the other two.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different model integrations: PenguinVL vs Voxtral TTS. Shared auto/docs plumbing is expected for any new model, but the code and purpose are unrelated." + "reason": "Different models and different code paths: PenguinVL vs Voxtral TTS. Shared auto-registration/docs scaffolding is expected for new model additions, not evidence of the same change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different model integrations: PenguinVL vs DeepSeek-OCR-2. They touch similar registration files, but implement separate architectures and do not appear mergeable as one PR." + "reason": "Different model implementations: PenguinVL vs DeepSeek-OCR-2. They touch similar framework files but introduce unrelated architectures, processors, and tests." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "Different model integrations: DeepSeek-OCR-2 vs Voxtral TTS. The overlap is only in generic Transformers scaffolding, not the same concrete change or bug fix." + "reason": "Different model families and functionality: DeepSeek-OCR-2 vs Voxtral TTS. The overlap is only in generic Transformers integration files, so they are not the same PR-level change." } ] }, @@ -18452,12 +18320,12 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "572edba53e7ceb1dd52f3d8ebbe0513bec879a4e6dd180690fa0f6c8670fb5f0", + "prepared_review_unit_hash": "a9e8623ca9c99c1c862dbe97653f089d2a1703b53431d09177a71c8d7b128c04", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4408, + "serialized_chars": 4407, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -18465,7 +18333,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4408, + "serialized_chars": 4407, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -18474,18 +18342,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related around module/kernel fusion, but they do not look like the same underlying change. #44979 adds a new Module Fusion API and test coverage; #45363 wires n-to-1 kernel fusion through KernelConfig and model-loading paths with an example. They are conceptually adjacent but not duplicates.", - "confidence": 0.91, + "summary": "These PRs are related in theme (module/kernel fusion), but they are not the same underlying change: one adds a general Module Fusion API, while the other wires KernelConfig-based n-to-1 fusion into model loading and integrations.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR duplicate here: #44979 is an API layer for module fusion, while #45363 is a separate kernel-fusion integration change across loading/integration code.", + "canonical_pr_reason": "PR #45363 is the broader, end-to-end feature implementation: it touches model loading, integrations, and KernelConfig plumbing, making it the better representative of the cluster than the lower-level API scaffold in #44979.", "best_issue_reason": null, - "best_pr_reason": "#45363 is the better representative for the cluster topic because it is the more end-to-end, user-facing fusion implementation and touches the concrete code paths where fusion is enabled.", + "best_pr_reason": "PR #45363 is the most complete and user-facing change in the set; it demonstrates the actual fusion workflow and integrates it across the library, whereas #44979 is mainly a foundational API addition.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Related theme, but different concrete changes: one introduces a module-fusion API, the other implements n-to-1 kernel fusion plumbing via KernelConfig. They would not plausibly be merged into a single duplicate PR." + "reason": "Related area, but different concrete changes and code paths: #44979 introduces a standalone Module Fusion API, while #45363 implements KernelConfig-driven n-to-1 fusion integration. They could not reasonably be merged as one PR without conflating distinct layers of the feature." } ] }, @@ -18515,12 +18383,12 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "d51656b6d00d95ed7ff006f8a6aa41b3e9d6cc21ef95ecd6541eeaf37e25ba75", + "prepared_review_unit_hash": "b9496540d462586eae3427e382e5059abc9daad5386b2365fba55d580a13cc61", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4413, + "serialized_chars": 4414, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -18528,7 +18396,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4413, + "serialized_chars": 4414, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -18537,18 +18405,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests patch the same _patch_mistral_regex AttributeError in the same file and target the same issue, with the second PR adding test coverage. They look like duplicates and could plausibly be merged into one fix.", + "summary": "Both pull requests address the same AttributeError in `_patch_mistral_regex` by switching from `tokenizer.backend_tokenizer.pre_tokenizer` to `tokenizer.pre_tokenizer` in the same file. PR #45317 is the stronger canonical candidate because it carries the same fix plus test coverage.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45317 is the better canonical PR because it contains the same code fix as #45086 plus test coverage and slightly broader discussion/activity, making it the more complete representative.", + "canonical_pr_reason": "PR #45317 is the better canonical PR because it implements the same fix as #45086 and also includes test changes, making it the more complete change set.", "best_issue_reason": null, - "best_pr_reason": "PR #45317 is the best overall representative of the change: same fix, same target issue, and it includes verification tests. #45086 is the thinner precursor.", + "best_pr_reason": "PR #45317 is the best representative of the cluster: same concrete bug fix, same code path, and it adds validation via tests.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying bug fix in _patch_mistral_regex, same target issue, same code path, and the later PR adds tests rather than changing scope; they are duplicate-level similar." + "reason": "Same underlying AttributeError fix in the same function and file; #45317 is a later, test-augmented version of the same change, so they are merge-equivalent enough to treat as duplicates." } ] }, @@ -18578,7 +18446,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "dd05c3f80dbb609fa5ec832dda14ff799d9efb7de041c77241b26037716abe8a", + "prepared_review_unit_hash": "f1b228e661d35cc19ece2db3d53c86ed321d1f963a860b60736bc9108957ef84", "component_budget": { "node_count": 2, "item_count": 2, @@ -18600,18 +18468,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open NemotronH PRs overlap on shared model files, but they target different changes: one is a structural refactor/conversion-mapping update, the other splits NemotronH into dense/sparse variants with docs and auto-mapping updates. They are related, not duplicates.", - "confidence": 0.86, + "summary": "Two open NemotronH-related PRs overlap on shared model files, but they are not duplicates: one is a refactor/conversion-mapping change, the other is a broader model-family split into dense/sparse variants with docs and tests.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45569 is the broader, more user-facing change: it introduces the dedicated NemotronHDense/NemotronHSparse variants, updates docs and auto-mapping, and appears to subsume the model-splitting direction more completely.", + "canonical_pr_reason": "PR #45569 is the better canonical PR because it is the broader, more complete change: it introduces dedicated nemotron_h_dense/nemotron_h_sparse packaging, docs, auto-mapping updates, and tests, whereas #45115 is a narrower refactor focused on inheritance and checkpoint conversion renames.", "best_issue_reason": null, - "best_pr_reason": "PR 45569 is the best representative because it covers the full architectural reorganization and public API/docs surface, while PR 45115 is a narrower internal refactor focused on conversion key renames and inheritance plumbing.", + "best_pr_reason": "PR #45569 best represents the cluster because it covers the end-state architecture and user-facing model organization for NemotronH, not just internal renaming/refactoring.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Overlapping NemotronH internals, but not the same fix: 45115 is a refactor/conversion-mapping/inheritance change, while 45569 adds separate dense/sparse model variants plus docs and auto-mapping changes. They could coexist, but they are not one mergeable PR for the same underlying bug/change." + "reason": "Shared NemotronH files do not imply the same change. #45115 is a conversion/architecture refactor toward GraniteMoeHybrid-compatible naming, while #45569 splits NemotronH into dense/sparse model packages and adds docs/tests. They touch related subsystems but are different concrete changes and would not naturally merge into one PR." } ] }, @@ -18641,7 +18509,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "a1af9e461c784e1bac082be504bf8201b663b6ead12f3c88dfdc8795aa2e25f1", + "prepared_review_unit_hash": "fda8a7937bd06ad8b4986e85c21bcebd3da6a62f10d06dfb9e0495bc6dc77001", "component_budget": { "node_count": 2, "item_count": 2, @@ -18663,18 +18531,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Related feature work, but not duplicates: PR 45333 adds heterogeneous per-layer config plumbing, while PR 45332 extends cache/modeling code to use that support.", - "confidence": 0.87, + "summary": "These are related but distinct PRs: #45333 adds per-layer heterogeneous config plumbing, while #45332 builds on that to add broader heterogeneous model/cache/modeling support. They share files and theme, but they do not look like the same concrete change.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45332 is the broader, more representative artifact because it covers the end-to-end heterogeneous model path, not just config plumbing.", + "canonical_pr_reason": "#45333 is the cleaner, more self-contained PR: it introduces the per-layer configuration foundation without the additional modeling/cache changes present in #45332.", "best_issue_reason": null, - "best_pr_reason": "PR 45332 is the best representative of the cluster if one must be chosen, since it subsumes the config work and adds the actual modeling/cache integration.", + "best_pr_reason": "#45333 is the best representative of the cluster theme because it is the narrower foundational change; #45332 is a later, broader follow-on rather than a duplicate.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "They are closely related feature PRs, but not the same underlying change: 45333 adds per-layer heterogeneous config support, while 45332 implements broader model/cache behavior on top of that. They could stand as separate PRs and are not safe to merge as duplicates." + "reason": "Do not merge: #45333 is config-only plumbing, while #45332 adds heterogeneous model/cache behavior and touches multiple runtime code paths. They are related and likely sequential, but not the same fix/change." } ] }, @@ -18704,7 +18572,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "431c69196f7cd7d336851b59ab40e4147871aee336a72583341cd000c34592c3", + "prepared_review_unit_hash": "97f0812e47929da852c7e9566360b41f17e004479ec927ba5acfdd82e90c97b6", "component_budget": { "node_count": 2, "item_count": 2, @@ -18726,18 +18594,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests are typing-related and overlap in a few files, but they are not the same change: PR 45415 is a broad repo-wide type-checking sweep, while PR 45425 adds specific typing protocols/aliases and related modeling_utils support. They are related work, not duplicate fixes.", - "confidence": 0.84, + "summary": "Two open PRs are related to typing cleanup, but they address different changes: one is a broad repo-wide type-checking sweep, the other adds specific typing protocols/helpers for core model-loading paths. They are not duplicates.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45425 is the more focused and self-contained typing change; PR 45415 is a much broader type-checking pass across many files.", + "canonical_pr_reason": "PR 45425 is the more focused and reusable typing-infra change, adding protocol aliases in _typing.py and wiring them into core utilities; PR 45415 is a broader type-checking pass across many files.", "best_issue_reason": null, - "best_pr_reason": "PR 45425 is the better representative of the narrower concrete typing refactor, whereas PR 45415 is a large sweeping enablement change and not the same underlying fix.", + "best_pr_reason": "PR 45425 is the best standalone candidate because it makes a concrete, narrowly scoped typing change with clear code-path impact, whereas PR 45415 is an umbrella type-checking sweep across unrelated modules.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Overlapping typing scope and some shared files, but PR 45415 is a broad type-checking rollout and PR 45425 adds specific type aliases/protocols for modeling_utils/PEFT; they do not fix the same concrete code-path problem." + "reason": "Both are about typing, but they do not fix the same underlying problem. 45415 is a broad type-checking enablement/cleanup PR across many files; 45425 adds specific typing protocols and modeling_utils-related support. They could both land independently." } ] }, @@ -18772,12 +18640,12 @@ "pull_request:45817|pull_request:45843", "pull_request:45836|pull_request:45843" ], - "prepared_review_unit_hash": "c4a72e4167a84aa143d7acb0f874d7891c780d227b317b198662f7a122c5afb7", + "prepared_review_unit_hash": "dc05f245832eebd69d40f902f011df55be67eb2f2dcb6ae9e728e410f776af87", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 4, - "serialized_chars": 10386, + "serialized_chars": 10388, "estimated_input_tokens": 2597, "estimated_eval_tokens": 5450 }, @@ -18785,7 +18653,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 4, - "serialized_chars": 10386, + "serialized_chars": 10388, "estimated_input_tokens": 2597, "estimated_eval_tokens": 5450 }, @@ -18794,36 +18662,36 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are all in the same broad area of model-parallel/device-placement stability, but they target different models and different concrete problems, so they should not be merged as duplicates.", - "confidence": 0.88, + "summary": "These are separate pull requests fixing different model-parallel issues in different model families; one PR is only a test skip. They are related by theme but not the same underlying change, so no soft merges should be accepted.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: 45487 fixes AltCLIP/ChineseCLIP device placement, 45817 fixes Gemma4 model-parallel handling, 45843 fixes Deimv2 backbone split propagation, and 45836 only skips failing tests for MiniCPM-V/Qwen3.5. They are related in theme but not the same change.", + "canonical_pr_reason": "PR 45487 is the broadest and most representative concrete code fix in the set: it adjusts device placement for token type ids and updates model-parallel-related module lists across multiple affected models, with corresponding tests.", "best_issue_reason": null, - "best_pr_reason": "PR 45817 is the strongest standalone representative because it contains an actual code-path fix for a specific model-parallel bug plus a clear model-specific scope and test coverage.", + "best_pr_reason": "PR 45487 is the best overall representative PR because it contains an actual runtime fix rather than a test-only skip, and its changes are more central to the shared model-parallel failure mode than the narrower model-specific patches.", "soft_edge_verdicts": [ { "left": "pull_request:45487", "right": "pull_request:45843", "accept": false, - "reason": "Different models and different fixes: AltCLIP/ChineseCLIP token-type device placement vs Deimv2 backbone split propagation. Same theme, not the same underlying bug." + "reason": "Both are model-parallel fixes, but they target different architectures and different root causes: AltCLIP/ChineseCLIP token-id device placement vs. Deimv2 backbone _no_split_modules propagation. Too different to treat as the same change." }, { "left": "pull_request:45487", "right": "pull_request:45836", "accept": false, - "reason": "45836 only skips invalid tests for MiniCPM-V/Qwen3.5; 45487 fixes device placement in AltCLIP/ChineseCLIP. Not the same code-path issue." + "reason": "PR 45836 is a test skip for MiniCPM-V/Qwen3.5 cache incompatibility, not a code fix for the same bug as 45487. Different problem and different scope." }, { "left": "pull_request:45817", "right": "pull_request:45843", "accept": false, - "reason": "Both are model-parallel related, but they fix different model implementations and different failure modes. Too broad to treat as one duplicate PR." + "reason": "Gemma4 fixes a device-placement/helper and module-splitting issue in Gemma4; Deimv2 propagates _no_split_modules from a backbone. Same broad theme, but not the same concrete bug or mergeable PR." }, { "left": "pull_request:45836", "right": "pull_request:45843", "accept": false, - "reason": "45836 is a test-skip cleanup, while 45843 is a code fix in Deimv2. They do not share the same underlying bug or mergeable change." + "reason": "Test-only skip for incompatible quantized cache is unrelated to Deimv2 model-parallel module splitting. Not the same underlying issue." } ] }, @@ -18853,7 +18721,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "f749a2afe4545eda49a78ad39a75e1649ab44e7a72e973ecc3d1f277e9ae9a5e", + "prepared_review_unit_hash": "17044c1ce436e4b9fc9034c053ede3e9d160fe33424df392264b9902bc83af7f", "component_budget": { "node_count": 2, "item_count": 2, @@ -18875,18 +18743,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two pull requests both touch EP-related loading paths, but they address different concrete failures: one fixes EP + ZeRO-3 loading via accelerate launch, while the other fixes experts being overwritten during FSDP2/rank-0 broadcast. They are related, but not the same underlying bug/change.", - "confidence": 0.91, + "summary": "These PRs share the EP/transformers area, but they fix different bugs: one is about EP + DeepSpeed ZeRO-3 loading/serialization via accelerate launch, the other about EP + FSDP2 rank-0 broadcast overwriting experts. They are not duplicates and should not be merged into one PR.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "No clear canonical duplicate PR here; the two PRs solve different EP code-path bugs. If a single representative PR had to be picked, 45662 is the broader and more substantive fix, but it should not subsume 45548.", + "canonical_pr_reason": "pull_request:45662 is the better representative because it targets a specific, concrete failure mode with a focused code-path fix (expert parameters being overwritten during shard/broadcast handling).", "best_issue_reason": null, - "best_pr_reason": "pull_request:45662 is the stronger representative of the cluster because it targets a concrete EP corruption bug in distributed loading/broadcast paths and spans more of the affected code, whereas 45548 is a narrower serialization/loading fix for a different failure mode.", + "best_pr_reason": "pull_request:45662 is the strongest standalone PR in this cluster: the problem statement is precise, the affected path is clear, and the fix is narrowly aligned to that bug.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Same general EP area, but different bugs and code paths: 45548 fixes loading via accelerate/ZeRO-3 and config serialization of distributed_config, while 45662 fixes experts being overwritten by rank-0 broadcast during FSDP2 handling. Not mergeable as one PR." + "reason": "Both concern EP/loading, but 45548 fixes config serialization and EP detection for ZeRO-3/accelerate, while 45662 fixes expert parameters being overwritten during FSDP2/broadcast; different underlying bugs and code paths." } ] }, @@ -18916,12 +18784,12 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "4fc6df5c20a310d140cb28a298e8a91920250f7ed3ce703dcb095c2f65b61fc0", + "prepared_review_unit_hash": "2c646fcc1a3c36f0baeb4841a86bcd4832aa9914d85867b7e82ccf5144437d4c", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, + "serialized_chars": 4590, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -18929,7 +18797,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, + "serialized_chars": 4590, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -18938,18 +18806,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs address the same underlying xdist collision problem around `captured_info` debug artifacts. PR #45645 is the broader, more complete fix because it covers both the writer-side file splitting and the CI-side log collection changes; PR #45639 is a narrower subset of that change.", - "confidence": 0.88, + "summary": "Both PRs address the same xdist/captured_info collision problem in Transformers testing utilities. PR #45645 is the more complete fix because it includes the worker-safe file handling plus CI-side aggregation of multiple captured_info files, so it is the better cluster representative.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45645 is the better canonical PR because it implements the end-to-end fix: xdist-safe output file handling plus workflow updates to collect all `captured_info*.txt` artifacts.", + "canonical_pr_reason": "PR #45645 is the stronger canonical PR because it implements the xdist-safe artifact handling in code and also updates the CI workflow to read all captured_info shards, making it the more complete end-to-end fix.", "best_issue_reason": null, - "best_pr_reason": "PR #45645 is the strongest representative for the cluster since it resolves the same concrete bug more completely and includes the CI/log-preservation follow-up needed for the xdist-safe artifact change.", + "best_pr_reason": "PR #45645 best represents the cluster: it fixes the same captured_info/xdist collision path as #45639 but with the fuller solution and supporting workflow changes.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same underlying bug: xdist workers colliding on `captured_info` output. The second PR extends the same fix into CI artifact collection, so these are compatible parts of one change rather than unrelated edits." + "reason": "Same underlying bug: xdist workers colliding on captured_info output. #45645 builds on the same helper change and adds the workflow logic needed to consume per-worker files, so these are mergeable into one combined fix." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index 1303f4e8428c6c6561500d5b3f7d55aa583643a0..b42b7063d8da54c9097a45914d0b5e85448e4e16 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260509t060023z", + "analysis_id": "hybrid-model-20260509t120021z", "archived_artifacts": { - "hybrid": "snapshots/20260509T060023Z/analysis-runs/hybrid-model-20260509t060023z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260509T060023Z/analysis-runs/hybrid-model-20260509t060023z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-09T06:08:26Z", + "published_at": "2026-05-09T12:04:06Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260509T060023Z", + "snapshot_id": "20260509T120021Z", "variant": "hybrid" } diff --git a/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.json b/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..7d4fa7fdb241ef6a951c107edeabc5cec99c2086 --- /dev/null +++ b/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.json @@ -0,0 +1,2076 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260509T120021Z", + "generated_at": "2026-05-09T12:04:05Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.805, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.854, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 713, + 720 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 699, + 705 + ], + [ + 1301, + 1307 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43824-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43824, + "canonical_pr_number": 43836, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.532, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.543, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3529, + 3536 + ], + [ + 3753, + 3787 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44018-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44068, + "issue_numbers": [], + "pr_numbers": [ + 44018, + 44068 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44018, + "right_pr_number": 44068, + "code_similarity": 0.766, + "size_similarity": 0.939, + "file_overlap": 1.0, + "area_overlap": 0.425, + "patch_similarity": 0.866, + "shared_filenames": [ + "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "tests/models/gpt_neo/test_modeling_gpt_neo.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "left_ranges": [ + [ + 26, + 46 + ], + [ + 138, + 143 + ], + [ + 182, + 187 + ], + [ + 283, + 295 + ], + [ + 327, + 341 + ], + [ + 348, + 354 + ], + [ + 360, + 369 + ], + [ + 399, + 406 + ], + [ + 411, + 419 + ], + [ + 428, + 433 + ], + [ + 472, + 492 + ], + [ + 507, + 513 + ], + [ + 519, + 528 + ], + [ + 541, + 559 + ], + [ + 562, + 567 + ], + [ + 595, + 601 + ], + [ + 607, + 614 + ], + [ + 627, + 643 + ], + [ + 685, + 690 + ], + [ + 708, + 714 + ], + [ + 720, + 727 + ], + [ + 740, + 757 + ], + [ + 761, + 766 + ], + [ + 780, + 786 + ], + [ + 791, + 798 + ], + [ + 807, + 822 + ], + [ + 840, + 845 + ] + ], + "right_ranges": [ + [ + 26, + 31 + ], + [ + 34, + 44 + ], + [ + 136, + 141 + ], + [ + 180, + 185 + ], + [ + 281, + 293 + ], + [ + 325, + 339 + ], + [ + 346, + 352 + ], + [ + 358, + 367 + ], + [ + 397, + 404 + ], + [ + 409, + 417 + ], + [ + 426, + 434 + ], + [ + 463, + 483 + ], + [ + 498, + 504 + ], + [ + 510, + 519 + ], + [ + 532, + 550 + ], + [ + 553, + 564 + ], + [ + 586, + 592 + ], + [ + 598, + 605 + ], + [ + 618, + 634 + ], + [ + 676, + 688 + ], + [ + 699, + 705 + ], + [ + 711, + 718 + ], + [ + 731, + 748 + ], + [ + 752, + 762 + ], + [ + 771, + 777 + ], + [ + 782, + 789 + ], + [ + 798, + 813 + ], + [ + 831, + 836 + ] + ] + }, + { + "filename": "tests/models/gpt_neo/test_modeling_gpt_neo.py", + "left_ranges": [ + [ + 458, + 464 + ] + ], + "right_ranges": [ + [ + 458, + 464 + ] + ] + } + ] + } + ] + } + ], + "duplicate_issues": [], + "duplicate_prs": [ + { + "cluster_id": "cluster-41115-3", + "canonical_pr_number": 45613, + "duplicate_pr_numbers": [ + 41116 + ], + "target_issue_number": 41115, + "reason": "PRs in cluster-41115-3 are treated as duplicates because they converge on issue #41115 with closing_reference evidence." + }, + { + "cluster_id": "cluster-41211-3", + "canonical_pr_number": 44339, + "duplicate_pr_numbers": [ + 41356 + ], + "target_issue_number": 41211, + "reason": "PRs in cluster-41211-3 are treated as duplicates because they converge on issue #41211 with closing_reference evidence." + }, + { + "cluster_id": "cluster-43240-3", + "canonical_pr_number": 43251, + "duplicate_pr_numbers": [ + 43254 + ], + "target_issue_number": 43240, + "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43698-3", + "canonical_pr_number": 43779, + "duplicate_pr_numbers": [ + 43816 + ], + "target_issue_number": 43698, + "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43824-3", + "canonical_pr_number": 43836, + "duplicate_pr_numbers": [ + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43979-11", + "canonical_pr_number": 44007, + "duplicate_pr_numbers": [ + 43996, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "target_issue_number": 43979, + "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-44018-2", + "canonical_pr_number": 44068, + "duplicate_pr_numbers": [ + 44018 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-45081-3", + "canonical_pr_number": 45317, + "duplicate_pr_numbers": [ + 45086 + ], + "target_issue_number": 45081, + "reason": "PRs in cluster-45081-3 are treated as duplicates because they converge on issue #45081 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45561-3", + "canonical_pr_number": 45645, + "duplicate_pr_numbers": [ + 45639 + ], + "target_issue_number": 45561, + "reason": "PRs in cluster-45561-3 are treated as duplicates because they converge on issue #45561 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45647-3", + "canonical_pr_number": 45738, + "duplicate_pr_numbers": [ + 45737 + ], + "target_issue_number": 45647, + "reason": "PRs in cluster-45647-3 are treated as duplicates because they converge on issue #45647 with closing_reference, shared_issue_target evidence." + } + ], + "best_issue": { + "cluster_id": "cluster-45647-3", + "issue_number": 45647, + "reason": "Issue #45647 is the strongest global issue candidate because it is open, belongs to a cluster with 3 artifacts, and carries 12 discussion comments plus 8 inbound references.", + "score": 162.0 + }, + "best_pr": { + "cluster_id": "cluster-43979-11", + "pr_number": 44007, + "reason": "PR #44007 is the strongest global PR candidate because it is open, belongs to a cluster with 11 artifacts, links to 1 issues, and carries 2 review/discussion events.", + "score": 238.886 + } +} diff --git a/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..e94706a15634edca6b91dd3a73d9f890b707eecf --- /dev/null +++ b/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,18961 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260509T120021Z", + "generated_at": "2026-05-09T12:04:05Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "6bf651a68b2d723bbbf9fa2370230f1543b4039ed2190305558c5fd903edea3a", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are only loosely related by theme, but they describe different problems: tokenization mismatch, private-model auth/error messaging, and a generic model-loading failure. I would not merge any of them as duplicates.", + "confidence": 0.88, + "canonical_issue_reason": "issue #16618 is the most generic and discussion-heavy of the three, so it is the best representative if one must be chosen, but it still appears to be a distinct bug from the other two.", + "canonical_pr_reason": null, + "best_issue_reason": "#16618 is the best issue to anchor the cluster because it is the broadest model-loading report and has the most activity, but it should not subsume the others as a duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Tokenization behavior matching TensorFlow code is a different subsystem and failure mode from being unable to load a model." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "#15980 is about the error shown when downloading a private model without login, while #16618 concerns failing to load 'bert-base-uncased'; same area, but not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41093", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43792", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45070", + "issue:45081", + "issue:45084", + "issue:45161", + "issue:45237", + "issue:45362", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45800", + "issue:45823" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44805|issue:45823", + "issue:43638|issue:44805", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43039|issue:45161", + "issue:43975|issue:44457", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:43828|issue:45161", + "issue:43425|issue:44292", + "issue:44918|issue:45161", + "issue:34928|issue:41720", + "issue:43716|issue:45685", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "issue:45507|issue:45685", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44560|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:34928|issue:36010", + "issue:43039|issue:44805", + "issue:43901|issue:44512", + "issue:41762|issue:43596", + "issue:39290|issue:41720", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:39290|issue:43531", + "issue:41093|issue:43638", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:43792|issue:45070", + "issue:45362|issue:45464", + "issue:43404|issue:43866", + "issue:39290|issue:45823", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:45800|issue:45823", + "issue:41093|issue:41762" + ], + "prepared_review_unit_hash": "f58c354d214dcb2df40150e9fa284b06a36d4ee3965eb8d0d583aa0bc5878760", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 71, + "serialized_chars": 48865, + "estimated_input_tokens": 12217, + "estimated_eval_tokens": 24690 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a mix of unrelated model-specific bugs and doc issues; only one pair looks like a true duplicate. The strongest duplicate is the Bert/DeepSpeed ZeRO-3 index-out-of-bounds reports.", + "confidence": 0.76, + "canonical_issue_reason": "issue:43596 is the best representative because it states the core failure clearly and broadly (index 0 out of bounds with DeepSpeed ZeRO-3 and BertModel), and it has a strong duplicate counterpart in issue:43638.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43596 is the clearest anchor for the shared Bert/ZeRO-3 out-of-bounds bug among the issues here; the rest are either different models, different error classes, or documentation cleanups.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different Qwen3.5 failures: one is a missing config attribute, the other is a streaming chat/completions API issue." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated problems: GPT-OSS on AMD GPUs vs an MPS histogram error in a MoE path." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different model families and failure modes: image-preprocessor dtype mismatch vs AMD GPU runtime failure." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Both mention dtype/runtime issues, but they are different models and different concrete code paths." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "GPT-OSS AMD GPU failure is not the same bug as GraniteMoEHybrid calling an invalid method." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different model-specific runtime errors; no clear shared code-path." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "Both are model/runtime failures, but one is DeepSpeed ZeRO-3 collectives and the other is ONNX export." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Different model/export issues: ModernBERT ONNX export vs Qwen3Moe FineGrainedFP8." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export and auto device-mapping cuda assert are unrelated." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 doc cleanups, but they fix different stale references (pipeline tasks vs run command)." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export bug is unrelated to the GenerationMixin import error." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Both are shape/device-style errors, but one is a mask/tensor index mismatch and the other is a Gemma4 PLE device-mapping bug." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Similar index errors, but one is a ZeRO-3 Bert initialization bug and the other is a generic mask-vs-tensor shape mismatch." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Same broad index-error wording, but the specific trigger differs: ZeRO-3 Bert init vs mask/tensor shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Different issues: generic mask index mismatch vs GPT-OSS MoE tensor-parallel problem." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Embedding unpacking with TRL is not the same as a mask/tensor shape mismatch." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice_preset and ModernBERT ONNX export are unrelated." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both involve DeepSpeed, but one is collective mismatch and the other is Bert ZeRO-3 index-out-of-bounds." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same underlying ZeRO-3 Bert bug with the same out-of-bounds error; 43638 is just a more specific reproduction." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger Kernel cross-entropy invocation is unrelated to GPT-OSS MoE tensor-parallel behavior." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Different problems: detokenization regression vs LoRA save/load output mismatch." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime failure is not the same as LoRA merge/save/load inconsistency." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Both are training-time failures, but FSDP checkpointing mismatch is different from the mask/tensor index error." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both are DeepSpeed-related, but the concrete failures are different and not the same code-path." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "Bert ZeRO-3 index-out-of-bounds is unrelated to GPT-OSS MoE tensor-parallel failure." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Activation checkpointing/FSDP size mismatch and CustomTrainer keyword mismatch are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Different model families and different failure classes." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Image-preprocessor dtype mismatch and invalid method call are different bugs." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3 config attribute missing and Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Autocast dtype mismatch and GPT-OSS MoE tensor-parallel issues are different." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "TRl SFT embedding unpacking failure is unrelated to GPT-OSS MoE TP behavior." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "FSDP checkpoint/activation mismatch is unrelated to auto device-map cuda asserts." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Mistral-3 image dtype mismatch and MPS histogram-not-implemented are different bugs." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Grouped_mm tracing error and image-preprocessor dtype mismatch do not share the same underlying bug." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Autocast dtype mismatch and Qwen-3-8B-NVFP4 runtime failure are different concrete problems." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Invalid method call in GraniteMoEHybrid is not the same as the MPS histogram error." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different models and different failure modes." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "NVFP4 runtime failure and TRL SFT embedding unpacking are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross_entropy path is not the same issue as Qwen3.5 embedding unpacking." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Both mention ZeRO-3 and index errors, but Gemma3 loading and Bert initialization are different bugs." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions from v5 removals, but they concern different removed references." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Mistral-3 dtype mismatch and Qwen3-vl video StopIteration are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Autocast dtype mismatch and MPS histogram-not-implemented are different runtime errors." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3-vl video processing failure is unrelated to the MPS MoE histogram issue." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "These are both floating-point/runtime issues, but not the same model, layer, or error path." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch and trainer API keyword mismatch are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "FSDP activation checkpointing bug and GenerationMixin import failure are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger Kernel cross_entropy invocation and mask/index shape mismatch are different bugs." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "These are separate docs issues: text-classification return_all_scores vs removed run command." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": false, + "reason": "Both are ZeRO-3-related index errors, but they occur in different model initialization paths." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Missing sliding_window_pattern and cudaErrorAssert on device mapping are not the same defect." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure for Voxtral-Mini is unrelated to Gemma4 device-mapping mismatch." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Cross-entropy being called under Liger Kernel is unrelated to a video-processing StopIteration." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Different model loading failures for different checkpoints." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Both are loading/test failures, but they involve different models and likely different causes." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Both mention sliding_window, but Gemma3TextConfig and Qwen3-MoE are different config bugs." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Generic mask/tensor shape mismatch and ZeRO-3 Bert index-out-of-bounds are not the same issue." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch-version compatibility and Pydantic PretrainedConfig field breakage are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "ZeRO-3 Bert index-out-of-bounds is unrelated to torch/transformers version incompatibility." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper model load failure and pydantic config-field breakage are unrelated." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is a chat crash and the other is a streaming API failure; not enough to treat as the same bug." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Mistral3 lm_head weight tying and Ovis2 checkpoint corruption are different problems." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "Torch/transformers compatibility and Gemma4 device-mapping mismatch are unrelated." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are shape/index runtime errors, but they are not the same code-path or model family." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft-edge pair, issue:43596 vs issue:43638, is a plausible duplicate on the shared Bert/DeepSpeed ZeRO-3 index-out-of-bounds failure. The other pairwise rejections are appropriately cautious and do not overclaim equivalence based on generic similarity alone." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 2, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:39186", + "issue:39692", + "issue:40990", + "issue:41093", + "issue:42915", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43828", + "issue:43866", + "issue:43873", + "issue:43950", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44492", + "issue:44512", + "issue:44530", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45161", + "issue:45399", + "issue:45464", + "issue:45507", + "issue:45542", + "issue:45632", + "issue:45685", + "issue:45698", + "issue:45800" + ], + "soft_pairs": [ + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:44387|issue:45005", + "issue:43541|issue:45161", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:45020|issue:45800", + "issue:43531|issue:45070", + "issue:43541|issue:44589", + "issue:41093|issue:43596", + "issue:43054|issue:43994", + "issue:45542|issue:45800", + "issue:43716|issue:44918", + "issue:44918|issue:45685", + "issue:45632|issue:45698", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:40990|issue:44960", + "issue:44530|issue:45005", + "issue:44360|issue:44512", + "issue:42915|issue:45399", + "issue:44863|issue:45005", + "issue:43873|issue:45005", + "issue:39186|issue:44918", + "issue:44492|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:43644|issue:43950", + "issue:44292|issue:45507", + "issue:39692|issue:43054", + "issue:43828|issue:44928", + "issue:43866|issue:44403" + ], + "prepared_review_unit_hash": "855b8f98540366ed93fc12f1017303dc3eb375868b28381b17c0260c71659dc5", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37471, + "estimated_input_tokens": 9368, + "estimated_eval_tokens": 18992 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most candidates are false positives across unrelated model-, config-, and runtime-specific regressions. The only clear duplicate cluster here is the Transformers v5 non-persistent buffer corruption regression (43644/43950/44534).", + "confidence": 0.91, + "canonical_issue_reason": "issue:43950 is the clearest representative: it states the regression mechanism explicitly (`from_pretrained` corrupts non-persistent buffers) and matches the same underlying bug as 43644 and 44534.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43950 is the best global issue representative because it is the most specific about the root cause and regression scope, making it the strongest anchor for the duplicate cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "Different problems: vLLM loading failure for PaddleOCR-VL vs adding GGUF/gpt-oss architecture support." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Both involve config regressions, but the symptoms and fields differ (`pad_token_idx` vs `PretrainedConfig` pydantic breakage)." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/OOM regression vs tied-weights regression; unrelated code paths." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Both mention MoE/GPT-OSS-like models, but one is a grouped_mm tracing failure and the other is a tensor-parallel support issue." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Different failures: autocast dtype mismatch in Phi MoE vs streaming chat/completions failure in Qwen3.5." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "init_empty_weights argument handling is unrelated to the pydantic PretrainedConfig regression." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "Model-architecture support request vs streaming inference API failure; not the same bug." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Broad version incompatibility complaints, but one is remote_code breakage and the other is a torch/transformers mismatch." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug is unrelated to the PretrainedConfig pydantic regression." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Grouped_mm tracing error vs missing Float8 storage type; different runtime failures." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are indexing errors, but the shapes and triggers differ substantially." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but one is a relative embedding-quality complaint and the other is a pipeline/AutoModel nonsense-output report; not clearly the same bug." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard/TensorFlow backend detection issue is unrelated to torch-transformers version incompatibility." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Image preprocessor/model dtype mismatch vs Qwen3.5 input-embedding unpacking failure; different code paths." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "TRL SFT unpacking failure and an MPS histogram integer error are unrelated." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Both involve custom-code loading, but one is a cache-path collision and the other is loading the wrong module after save_pretrained; too different to merge confidently." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but the affected models and symptoms are different." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Notebook custom-model initialization regression is unrelated to flash-attn fallback gating." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "Perplexity anomaly on gpt-oss is unrelated to GLM5." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttention linear_attention crash and tied-weights regression are different failures." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "DSA indexer algorithm discussion vs documentation typo; unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "FineGrainedFP8Config failure is unrelated to flash-attn2 fallback checks." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint-loading failure is not the same as tied-weights regression." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization offloading behavior is unrelated to translation-model tied weights." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP weight-dimension error is unrelated to Qwen3.5/TRL input embedding unpacking." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategy typo and a removed CLI command doc issue are not duplicates." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "TRl embedding unpacking failure vs GraniteMoEHybrid invalid method call; different bugs." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Detokenization regression in DeepSeek-Coder is unrelated to Qwen-3-8B-NVFP4 runtime failure." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Same bug: v5 corrupts non-persistent buffers; the titles describe the same regression from two angles." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Direct duplicate: both report the non-persistent buffer corruption regression in Transformers 5.x." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Qwen NVFP4 runtime error and GraniteMoEHybrid invalid method are different failures." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "Docs example errors for SigLIP2 are not the same as a broader text-embedding quality complaint." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Autocast dtype mismatch in Phi MoE is unrelated to Qwen3.5 RLHF gradient explosion." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Corrupted checkpoint vs generic loading noise; not the same underlying bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet, and the only accepted duplicate cluster (43644/43950/44534) is supported by the titles. The other soft-edge rejections are conservative and do not overclaim sameness." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 3, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:41553", + "issue:41628", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43404", + "issue:43493", + "issue:43638", + "issue:43643", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43856", + "issue:43872", + "issue:43881", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:44220", + "issue:44368", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44509", + "issue:44589", + "issue:44661", + "issue:44910", + "issue:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45237", + "issue:45356", + "issue:45399", + "issue:45520", + "issue:45685", + "issue:45701", + "issue:45800", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:36331|issue:41762", + "issue:41628|issue:45800", + "issue:41553|issue:43883", + "issue:43872|issue:44589", + "issue:38175|issue:43054", + "issue:43054|issue:45701", + "issue:44910|issue:45859", + "issue:41553|issue:43881", + "issue:42947|issue:44387", + "issue:44403|issue:44451", + "issue:43643|issue:45020", + "issue:43975|issue:45520", + "issue:43054|issue:43493", + "issue:43975|issue:45237", + "issue:44403|issue:44488", + "issue:42947|issue:43856", + "issue:43881|issue:43883", + "issue:41762|issue:42915", + "issue:42491|issue:44368", + "issue:45685|issue:45823", + "issue:43975|issue:44451", + "issue:43824|issue:43872", + "issue:45020|issue:45823", + "issue:44991|issue:45399", + "issue:44661|issue:45020", + "issue:43828|issue:45823", + "issue:45020|issue:45356", + "issue:43782|issue:44960", + "issue:45081|issue:45399", + "issue:43827|issue:44509", + "issue:43404|issue:43950", + "issue:43792|issue:44220", + "issue:43742|issue:45399", + "issue:42915|issue:45020", + "issue:43638|issue:45823" + ], + "prepared_review_unit_hash": "2e13009c4d40ff7273c56a3a121b4409840c019103e3916ff804f93e36db50d0", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38223, + "estimated_input_tokens": 9556, + "estimated_eval_tokens": 19368 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a loose collection of Transformers 5.x regressions across different models and subsystems, not a tight duplicate cluster. The only strong soft duplicate here is the SigLIP2 quality/discrepancy pair; the rest are too far apart in concrete failure mode or code path. No PRs are present.", + "confidence": 0.36, + "canonical_issue_reason": "issue:45020 is the broadest representative of the cluster\u2019s dominant theme: recent Transformers versions breaking model loading/remote_code paths.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the best anchor because it is open, broadly scoped, and closest to the shared regression pattern across the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Trainer compute_loss kwarg mismatch and ZeRO-3 index error are unrelated failures." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "AutoImageProcessor import failure and torch/Transformers version incompatibility are different problems." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Voxtral tokenizer-loading error and Molmo tied-weights attribute error are different code paths." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Both are quantization-related, but Int8Params kwarg mismatch and missing Float8 storage are distinct bugs." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both mention SigLIP2 quality, but one is zero probabilities and the other is degraded embeddings; not enough to call the same bug." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality and tokenization changes are unrelated issues." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "FlashAttention packed-sequence crash and CPU-offload rotary embedding incompatibility are different failures." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Tokenizer error for Voxtral and GLM-4V loading failure are unrelated." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient checkpointing ineffectiveness and CUDA reserved-memory OOM are different symptoms with different likely causes." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading noise and a specific ScandiBERT load failure are not the same bug." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "AutoConfig missing fields under trust_remote_code is related in theme, but it is a different concrete failure than broad remote_code breakage." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization regression and flash_attn import KeyError are unrelated." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": true, + "reason": "These both point to the same SigLIP2 implementation discrepancy; 43054 is a symptom report and 43493 identifies the HF-vs-JAX mismatch." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Tokenizer detokenization and AMD GPU runtime support are unrelated." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Loading noise and a model-specific load failure are not the same underlying bug." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "LoRA checkpointing behavior and Qwen3 MoE memory inefficiency are different training issues." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "GLM-4V load failure and missing all_tied_weights_keys on Molmo are different model-specific bugs." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 loading error and Qwen3 MoE LoRA compatibility are unrelated." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-MoE HF4.x/HF5.x incompatibility and a tie_word_embeddings warning are not the same bug." + }, + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "MPS histogram support in MoE and Gemma4 device-mismatch forwarding are different device/runtime problems." + }, + { + "left": "issue:43975", + "right": "issue:44451", + "accept": false, + "reason": "Detokenization regression and ScandiBERT load failure are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Missing Qwen2.5-VL import and bitsandbytes Int8Params incompatibility are different issues." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Remote_code loading regressions and Gemma4 device placement mismatch are different code paths." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading failure and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Model-addition helper failure in tokenizer mappings and general remote_code breakage are not the same concrete bug." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch in Phi MoE and Gemma4 device mismatch are different runtime issues." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Remote_code breakage and Kimi-K2.5 tokenizer regression are distinct problems." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error and GLM5 are unrelated." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Mistral regex patch crash and flash-attn fallback blocking are different issues." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Whisper failing to run and a specific fbank helper issue may be related at a high level, but this is not enough to treat them as the same bug." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM loading key error and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Mistral3 weight-tying bug and non-persistent buffer corruption are different from from_pretrained internals." + }, + { + "left": "issue:45520", + "right": "issue:45859", + "accept": false, + "reason": "Python 3.13 flash_attn import failure and CPU-offload rotary embedding incompatibility are unrelated." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "ZeRO-3 index error with a non-pretrained Bert and Gemma4 device mismatch are different failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The only accepted soft pair, issue:43054 with issue:43493, is well supported by the shared SigLIP2 theme, while the other rejections avoid overclaiming sameness across distinct models or failure modes. No PR pairs are present." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 4, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:41093", + "issue:41553", + "issue:42617", + "issue:42915", + "issue:43257", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43824", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43872", + "issue:43940", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44805", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44991", + "issue:45161", + "issue:45305", + "issue:45313", + "issue:45325", + "issue:45538", + "issue:45588", + "issue:45663", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:43257|issue:43866", + "issue:43940|issue:45313", + "issue:45161|issue:45823", + "issue:43872|issue:44291", + "issue:41553|issue:44991", + "issue:42915|issue:43872", + "issue:43854|issue:44863", + "issue:36331|issue:41093", + "issue:44928|issue:45588", + "issue:43257|issue:45305", + "issue:41553|issue:44488", + "issue:43872|issue:45538", + "issue:44530|issue:44863", + "issue:41093|issue:44805", + "issue:44479|issue:44560", + "issue:24643|issue:30064", + "issue:43366|issue:43828", + "issue:45663|issue:45823", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:43550|issue:44910", + "issue:43645|issue:43646", + "issue:43366|issue:44589", + "issue:43950|issue:45325", + "issue:44560|issue:44918", + "issue:43824|issue:43957", + "issue:42915|issue:43957", + "issue:42617|issue:43366", + "issue:44661|issue:45823", + "issue:36010|issue:42915", + "issue:38175|issue:43994", + "issue:43632|issue:45834" + ], + "prepared_review_unit_hash": "4b607d2ec926aaab8873b57691419f0a7c960514b90f29db57d09a5c35e7f423", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36777, + "estimated_input_tokens": 9195, + "estimated_eval_tokens": 18646 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous, with a few loose thematic mini-clusters (custom model init/_is_hf_initialized, Qwen3.5 attention/position_ids, ZeRO-3 loading, tokenizer loading), but no strong duplicate group overall. No PRs are present.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43646 is the broadest, most generic report in the custom-model-initialization regression family, so it is the best provisional issue canonical; however, the cluster is too mixed to treat this as a true single-duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the closest thing to a cluster representative because it captures the general Transformers 5 custom model initialization breakage without narrowing to a specific environment.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Different models and failure modes: Qwen3 MoE conversion vs an Ovis2 checkpoint corruption report." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Both are ZeRO-3 loading failures, but they appear model-specific and not the same concrete bug." + }, + { + "left": "issue:45161", + "right": "issue:45823", + "accept": false, + "reason": "Tensor-parallel GPT-OSS MoE issue vs Gemma4 device-map mismatch; unrelated code paths." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": false, + "reason": "Shared `_is_hf_initialized` theme, but one is bitsandbytes constructor incompatibility and the other is `init_empty_weights` loading." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Both concern tokenizers, but one is a bad error message and the other is a real loading regression for a different model." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "FP8/Qwen3Moe failure and bitsandbytes `_is_hf_initialized` incompatibility are distinct bugs." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Both are model loading problems, but they involve different architectures and likely different fixes." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Trainer API keyword mismatch vs tensor mask shape mismatch; no shared code path." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "Both touch attention behavior, but one is Qwen3.5 RLHF NaNs and the other is a flash-attention `s_aux=None` crash." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Both are training-related, but one is missing Qwen3 MoE weight conversion and the other is gradient averaging with GAS." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer-loading problems for different models; not the same bug." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "`_is_hf_initialized`/bitsandbytes incompatibility is unrelated to CLIPTokenizer's absurd `model_max_length`." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "PagedAttentionCache group-type crash and NemotronH checkpoint loading failure are unrelated." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": false, + "reason": "The error text is similar, but there is no evidence these are the same underlying mask-shape bug." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both involve Qwen variants and video/position handling, but they are different regressions with different symptoms." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Training with DeepSpeed and void segmentation map processing are unrelated." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF GPT-OSS support and Phi-tiny-MoE autocast dtype mismatch are different issues." + }, + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states bug vs Gemma4 PLE device mismatch; separate failures." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Both mention Qwen3/GPT-OSS style models, but one is GGUF support and the other is sliding-window behavior." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Non-persistent buffer corruption and Kosmos2.5 OCR index error are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Both concern Qwen3.5 and attention, but one is torch.compile+SDPA and the other is flash-attention position_ids handling." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These look like the same Transformers 5 custom-model initialization regression, with one being a notebook-specific manifestation of the same bug." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF GPT-OSS support and missing Float8 storage are different compatibility problems." + }, + { + "left": "issue:43950", + "right": "issue:45325", + "accept": false, + "reason": "Buffer corruption regression vs Qwen2.5-VL rope-index scaling bug; different code paths." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both mention Qwen3.5 video/input handling, but one is a StopIteration video error and the other is embedding unpacking with TRL SFT." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Missing import for a specific model class vs meta-device loading breakage; not the same defect." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "FP8/Qwen3Moe and meta-device loading failures are different issues." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "Cannot run 3d_parallel.py and GGUF GPT-OSS support are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer mapping bug and Gemma4 PLE forward device mismatch are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "Importing GenerationMixin and Qwen3Moe FP8 failure are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": false, + "reason": "Both involve siglip2, but one is zero-probabilities behavior and the other is nonsensical AutoModel/pipeline output." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "`_is_hf_initialized` flag regression and Kosmos2.5 OCR long-input indexing are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative about the cluster being mixed. The chosen representative/canonical issue (43646) is reasonable, the one accepted soft-edge pair (43645\u201343646) is supported by the titles and appears mergeable as the same bug, and the rejection reasons for the other pairs do not overstate similarity. No PRs are present, as stated." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 5, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43404", + "issue:43454", + "issue:43596", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43708", + "issue:43720", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43994", + "issue:44075", + "issue:44155", + "issue:44387", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44560", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44877", + "issue:44910", + "issue:44960", + "issue:44977", + "issue:44991", + "issue:45030", + "issue:45276", + "issue:45292", + "issue:45313", + "issue:45335", + "issue:45357", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45584", + "issue:45588", + "issue:45812" + ], + "soft_pairs": [ + "issue:44155|issue:45584", + "issue:44877|issue:45030", + "issue:44560|issue:44805", + "issue:43638|issue:44661", + "issue:43317|issue:44756", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:38175|issue:39692", + "issue:43644|issue:44534", + "issue:45313|issue:45357", + "issue:45488|issue:45812", + "issue:44960|issue:44977", + "issue:44451|issue:44488", + "issue:42491|issue:43720", + "issue:43854|issue:43931", + "issue:41720|issue:42915", + "issue:43708|issue:44075", + "issue:42491|issue:45276", + "issue:43257|issue:43854", + "issue:43856|issue:43873", + "issue:42915|issue:44756", + "issue:42491|issue:43931", + "issue:39692|issue:43994", + "issue:43856|issue:44387", + "issue:43644|issue:43645", + "issue:44910|issue:45588", + "issue:45362|issue:45406", + "issue:42491|issue:45292", + "issue:44488|issue:44991", + "issue:45276|issue:45335", + "issue:43404|issue:43454" + ], + "prepared_review_unit_hash": "230ca532b7367ac1ff35c6c1f129eb0e21193ca676efca0acc9278ecf032a488", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36454, + "estimated_input_tokens": 9114, + "estimated_eval_tokens": 18484 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a collection of distinct Transformers regressions; only one pair is a clear duplicate. The strongest canonical issue is the non-persistent-buffer junk regression, with the later issue being a near-verbatim repeat.", + "confidence": 0.78, + "canonical_issue_reason": "Issue 43644 is the earliest and clearest report of the exact same non-persistent-buffer regression later restated in 44534, and its wording is broad enough to serve as the canonical issue for that duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43644 is the best issue to anchor the cluster because it is the cleanest exact duplicate target among the soft edges and represents a concrete, reproducible regression rather than a model-specific variant.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "Different models and different failure modes; both mention generation problems, but they do not describe the same underlying bug." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both involve config/loading validation, but the affected models and reported failures are different and not a clear shared code-path bug." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Unrelated errors: a Qwen3-vl video StopIteration versus a tensor mask shape mismatch." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "One is a DeepSpeed/BertModel zero3 init crash; the other is a tokenizer-mapping limitation in add-new-model-like." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Different problems: dequantized model offload loading versus mmap OOM on Strix Halo." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Different bug classes and code paths; one is zero3/BertModel indexing, the other is tokenizer mapping generation." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "No shared underlying bug beyond both being errors; the model/config contexts are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Same model family, but one is bad probabilities and the other is a documentation example with multiple setup errors; not the same concrete bug." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Near-verbatim duplicate: both report Transformers v5 filling non-persistent buffers with junk." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Both concern Qwen3.5, but one is ZeRO-3 loading of language_model weights and the other is save_pretrained writing wrong visual encoder keys." + }, + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and different concrete tokenizer behavior." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Different models and different failures; no shared bug is evident." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading complaints, but the titles do not identify the same underlying defect or code path." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Different subsystems: LoRA/qwen3_moe compatibility versus BitNet packed-weight handling." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Both are loading issues, but the reported model-specific failures are different and not clearly the same bug." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Qwen3 auto device mapping cuda assert is not the same issue as FineGrainedFP8Config failure." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Training schedule math versus optimizer argument handling; unrelated bugs." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "One is Qwen3 MoE LoRA compatibility; the other is resize_token_embeddings not propagating in Gemma4." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3 MoE weight conversion during accelerate+deepspeed is unrelated to GLM-4.7-Flash load failures." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Memory-usage complaint versus quantization/offloading behavior; too broad and not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Different failure domains: Qwen3Moe FP8 config versus mmap OOM on Strix Halo." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Different Qwen3-family loading failures with different symptoms and code paths." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Same model name, but the first is a docs-example error bundle while the second is an actual nonsensical-output regression; not clearly the same concrete bug." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both mention memory, but one is training inefficiency and the other is int4 quantization causing OOM; not the same issue." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "One is a buffer-initialization regression; the other is a custom-model notebook initialization issue." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both touch flash attention, but one is a Qwen3.5 packed-sequence misparse and the other is an AttributeError on sink-less models." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different products and failures: chat crash on Qwen3.5-35B versus Gemma4Processor missing _tokenizer in serve." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but they concern different models and no shared concrete defect is established." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": false, + "reason": "Similar API surface, but different model families and different affected submodules; too little evidence for one duplicate bug." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Different Qwen3.5 regression families: ZeRO-3 weight loading versus visual-encoder key persistence." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both involve lm_head tying, but they are separate model classes and the titles do not establish the same concrete code-path defect." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet and stays conservative overall. The only accepted soft edge is well supported by the near-identical titles for issues 43644 and 44534, and the rejected pairs generally avoid overclaiming duplicate status when the packet only shows superficial similarity. Minor phrasing like \u201cexact same regression\u201d is a bit stronger than the evidence, but not enough to overturn the overall precision." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 6, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43381", + "issue:43425", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43828", + "issue:43854", + "issue:43873", + "issue:43906", + "issue:43957", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44589", + "issue:44683", + "issue:44756", + "issue:44863", + "issue:44877", + "issue:44912", + "issue:44928", + "issue:44960", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:36010|issue:39404", + "issue:44164|issue:44291", + "issue:44402|issue:44488", + "issue:43425|issue:43957", + "issue:39692|issue:44960", + "issue:43335|issue:45663", + "issue:42947|issue:45704", + "issue:43873|issue:44387", + "issue:45663|issue:45759", + "issue:45663|issue:45859", + "issue:44155|issue:45823", + "issue:43854|issue:45216", + "issue:44387|issue:44756", + "issue:44291|issue:44756", + "issue:44292|issue:44912", + "issue:42947|issue:43381", + "issue:45684|issue:45698", + "issue:45276|issue:45292", + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:41720|issue:44155", + "issue:44479|issue:44877", + "issue:43646|issue:43708", + "issue:45588|issue:45663", + "issue:43854|issue:44960", + "issue:43957|issue:44756", + "issue:45292|issue:45335", + "issue:44402|issue:44451", + "issue:43828|issue:43957", + "issue:43645|issue:44164", + "issue:43257|issue:44863", + "issue:43425|issue:43828", + "issue:44589|issue:44756", + "issue:44683|issue:45823", + "issue:43906|issue:44530", + "issue:39404|issue:45701", + "issue:43425|issue:45823" + ], + "prepared_review_unit_hash": "d64e983d1894309b0656e07434a592f8ba49c4dd84edabac4e6e642542eeea4e", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 37, + "serialized_chars": 38777, + "estimated_input_tokens": 9695, + "estimated_eval_tokens": 19646 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of closed Transformers issues. I only see two plausible duplicate pockets: custom model initialization in Transformers 5.0, and resize_token_embeddings not updating output embeddings. The rest are related at a broad subsystem level but not the same concrete bug.", + "confidence": 0.74, + "canonical_issue_reason": "issue:43646 is the broadest clean statement of the Transformers 5.0 custom-model initialization regression; issue:43645 is the notebook-specific repro of the same bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the best cluster anchor because it is the most general, least context-specific report among the near-duplicate candidates and captures the underlying custom-model init failure cleanly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "Different failures: import path breakage vs Whisper pipeline return_language regression." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Both involve loading/saving, but one is extra_state handling and the other is init_empty_weights argument plumbing." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Same broad symptom class, but different models and no evidence of the same underlying tokenizer bug." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch version incompatibility is not the same bug as meta-device loading breakage." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Different model families and different issues; doc example errors vs GLM5 loading." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "Sparse-layer config bug and Gemma4 FSDP2 shared_kv_states bug are unrelated." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing/LoRA issue is unrelated to the apex RMSNorm memory leak." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both concern quantization memory behavior, but one is offloading not working and the other is int4 reserved-memory/OOM; not the same concrete bug." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma4 FSDP2 forward KeyError is unrelated to Qwen multimodal config unwrapping." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Different code paths: Gemma4 attention state rebuilding vs Qwen3.5 MoE rotary embedding offload compatibility." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 batch leakage and Gemma4 device-map mismatch are distinct model-specific bugs." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "GLM test loading failure is unrelated to Qwen3.5 save_pretrained regression." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Memory/OOM symptoms differ: quantization reserved-memory growth vs Strix Halo mmap OOM." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "Unexpected _is_hf_initialized argument and mmap OOM are unrelated." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Both are quantized model load problems, but different quantization formats and different failure modes." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Eval-mode checkpointing limitation is not the same as LoRA gradient checkpointing ineffectiveness." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "One is permissions propagation during save_pretrained; the other is loading the wrong custom module after save_pretrained." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Same underlying resize_token_embeddings bug; 45276 is the Gemma4-specific variant of 45292's broader output_embeddings failure." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Gradient checkpointing in eval mode and Qwen3.5 RLHF NaN from 3D position_ids are different bugs." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "extra_state serialization and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Qwen3 auto device mapping cuda assert is unrelated to AudioFlamingo3 track leakage." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Video-input regression and strict config loading are different issues." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization regression is unrelated to Trainer max_steps recalculation on checkpoint resume." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Flash-attention sinkless crash is unrelated to Gemma4 FSDP2 shared_kv_states rebuilding." + }, + { + "left": "issue:43854", + "right": "issue:44960", + "accept": false, + "reason": "Different GLM variants and different failures; no shared code-path evidence." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading breakage is unrelated to disabling mmap for Strix Halo." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": false, + "reason": "Both are resize_token_embeddings-related, but one is output_embeddings and the other is decoder.embed_tokens; not enough evidence of the same bug." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Different model-specific loading failures with no proof of a shared root cause." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch and meta-device loading failure are different problems." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Notebook custom-model init regression and extra_state save/load failure are distinct." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3 MOE conversion with accelerate+deepspeed and NemotronH checkpoint loading are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch 2.10 incompatibility and Phi-tiny-MoE autocast dtype mismatch are not the same bug." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup error is unrelated to mmap OOM on Strix Halo." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device mismatch are different failures." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "An isolated reproduction of an older issue is not the same as the Qwen3.5 PagedAttentionCache crash." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline return_language regression and tokenizer-version changes are different bugs." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch compatibility issue and Gemma4 forward device mismatch are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The custom-model init cluster around 43645/43646 and the resize_token_embeddings cluster around 45276/45292 are the only clearly supported duplicate pockets, and the other soft-edge rejections avoid overclaiming. " + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 7, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:32090", + "issue:36032", + "issue:39404", + "issue:40990", + "issue:42947", + "issue:43299", + "issue:43421", + "issue:43425", + "issue:43452", + "issue:43582", + "issue:43596", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43856", + "issue:43883", + "issue:43901", + "issue:43931", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44265", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44661", + "issue:44671", + "issue:44683", + "issue:44737", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45759", + "issue:45859" + ], + "soft_pairs": [ + "issue:43611|issue:43645", + "issue:43931|issue:44863", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:43901|issue:44509", + "issue:39404|issue:44912", + "issue:44265|issue:44898", + "issue:43299|issue:43931", + "issue:44479|issue:44805", + "issue:43425|issue:44918", + "issue:44589|issue:45084", + "issue:43856|issue:44756", + "issue:40990|issue:42947", + "issue:39404|issue:44671", + "issue:43994|issue:44079", + "issue:36032|issue:43452", + "issue:44164|issue:45759", + "issue:43596|issue:44683", + "issue:44671|issue:44991", + "issue:44991|issue:45081", + "issue:44737|issue:45859", + "issue:32090|issue:39404", + "issue:44164|issue:44479", + "issue:44488|issue:45081", + "issue:44661|issue:44683", + "issue:40990|issue:43421", + "issue:43582|issue:43632", + "issue:43611|issue:43644", + "issue:44206|issue:44220", + "issue:43716|issue:45084", + "issue:43883|issue:44488", + "issue:44488|issue:44987", + "issue:43643|issue:44530" + ], + "prepared_review_unit_hash": "4f1763c4d9a61d11bb9b5b0021478a4788c5d11aaceaff6e3e0188afbbec462a", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37676, + "estimated_input_tokens": 9419, + "estimated_eval_tokens": 19094 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is highly heterogeneous: most items are separate regressions across model loading, tokenizers, training, docs, and hardware-specific behaviors. None of the soft pairs look like true duplicates of the same underlying bug/change, so no mergeable canonical duplicate emerges.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue: the cluster mixes unrelated bugs and feature requests across different models, APIs, and subsystems.", + "canonical_pr_reason": "No pull requests are present in the cluster.", + "best_issue_reason": "No issue is a good global representative because the items do not share one underlying defect.", + "best_pr_reason": "No pull requests are present to evaluate as a canonical fix.", + "soft_edge_verdicts": [ + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both are v5 loading regressions, but one is about base_model_prefix handling and the other about custom model initialization in Jupyter; different code paths." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Both are model-loading failures, but they affect different model families and report different failure modes (shape mismatch vs checkpoint compatibility)." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "One is a Torch version incompatibility report; the other is an image preprocessor/model dtype mismatch. Different problems." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache/linear_attention crash and template-node compilation error are unrelated subsystems and failure modes." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are documentation issues, but they concern different pipeline/task docs and different removal/behavior mismatches." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper return_language pipeline regression and git-oss-20b MXFP4 quantization fallback are unrelated model/pipeline issues." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export with torch_compilable_check and Perceiver non-default resolution failure are different bugs in different code paths." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both involve Qwen3-VL loading, but one is a dev-version MoE loading break and the other is a specific checkpoint shape mismatch; not the same bug." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression for Qwen VL models and a generic mask-shape IndexError are not the same underlying issue." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch compatibility and TRL SFT unpacking of Qwen3.5 embeddings are separate failures." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup failure and template-node compilation error are unrelated." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory, but one is Qwen3 MoE training inefficiency while the other is Strix Halo mmap OOM; different root causes." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and ineffective gradient checkpointing with LoRA are distinct training/evaluation issues." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline regression and CamemBERT masked-LM prediction regression are unrelated model behaviors." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "Siglip2 nonsensical outputs and ModelOutput key assignment when previously None are different bugs." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5Tokenizer special-tokens conflict and gguf_file breaking AutoTokenizer/AutoModel loading are different loading problems." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "extra_state save/load handling and composite Qwen text_config unwrapping are separate serialization/config issues." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Deepspeed zero3/BertModel index error and compiled flex_attention torch>=2.9 failure are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT prediction regression and tokenizer loading failure for EMBEDDIA/est-roberta are different issues." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Different tokenizers and different failure points: est-roberta loading vs Mistral regex patch/backend_tokenizer crash." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both touch device placement/offload, but XLNet CPU arange placement and Qwen3.5 MoE rotary embedding offload incompatibility are not the same code path." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer GPU broadcast NoneType error and Whisper return_language regression are unrelated." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "Serialization of extra_state and video-input regression for Qwen VL models are different bugs." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Loading cjvt/sleng-bert and Mistral regex patch crash are unrelated tokenizer/model-loading failures." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "add-new-model-like mapping failure and flex_attention compilation failure are different subsystems." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and runtime special-token post-processor updates are unrelated." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "AppleSilicon allocator warmup TypeError and _is_hf_initialized flag regression are different failures." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "base_model_prefix loading and non-persistent buffer initialization are separate v5 regressions." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Both are audio-feature related, but one is an unsupported center argument regression and the other concerns _torch_extract_fbank_features specifically; not clearly the same bug." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Image preprocessor dtype mismatch and template-node compilation error are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Molmo tied-weights attribute error and sleng-bert loading failure are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Different model families and different load failures; no shared underlying bug." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "trust_remote_code AutoConfig field loss and PagedAttentionCache linear_attention crash are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 8, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:34567", + "issue:36032", + "issue:40444", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43452", + "issue:43482", + "issue:43531", + "issue:43540", + "issue:43541", + "issue:43632", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43819", + "issue:43883", + "issue:43994", + "issue:44062", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44466", + "issue:44530", + "issue:44534", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44877", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45507", + "issue:45584" + ], + "soft_pairs": [ + "issue:34567|issue:40444", + "issue:44811|issue:45584", + "issue:43644|issue:43646", + "issue:44451|issue:44987", + "issue:43541|issue:45084", + "issue:36032|issue:42915", + "issue:43452|issue:43482", + "issue:42915|issue:44530", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:43883|issue:44991", + "issue:43404|issue:44466", + "issue:36032|issue:43645", + "issue:45084|issue:45507", + "issue:43262|issue:43377", + "issue:43646|issue:44534", + "issue:44987|issue:44991", + "issue:43994|issue:44610", + "issue:44403|issue:45081", + "issue:43322|issue:43540", + "issue:43377|issue:43819", + "issue:42915|issue:45084", + "issue:43645|issue:44534", + "issue:44451|issue:45081", + "issue:45216|issue:45357", + "issue:44987|issue:45081", + "issue:44220|issue:44683", + "issue:44265|issue:44610", + "issue:43404|issue:45127", + "issue:43296|issue:43531", + "issue:43632|issue:44756", + "issue:44062|issue:44987", + "issue:42915|issue:44291", + "issue:36032|issue:43742", + "issue:43531|issue:44877" + ], + "prepared_review_unit_hash": "2b74febea85212e5e4a52814bb6f0b8c1ccb766074ef829f15161ce9ff9eac14", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38205, + "estimated_input_tokens": 9552, + "estimated_eval_tokens": 19360 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The packet mostly contains unrelated issues. Among the listed soft edges, only issue:45216 and issue:45357 are a clear duplicate pair. The non-persistent-buffer regression is still best anchored by issue:43644, but this packet does not include a soft-edge acceptance for issue:44534, so I\u2019m not treating that relationship as evidenced here.", + "confidence": 0.86, + "canonical_issue_reason": "issue:43644 is the best issue anchor because it is the clearest and broadest report of the non-persistent-buffer junk regression; however, the packet does not provide a soft-edge pair for 43644 versus 44534, so I\u2019m only using it as the canonical issue, not as a packet-supported duplicate match.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 is the strongest overall issue candidate for the non-persistent-buffer regression because the title is explicit and broad, but the soft-edge evidence in this packet does not directly pair it with 44534.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "Trainer token accounting and Qwen2.5-VL iterable-dataset/multi-image failures are different bugs." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper-related, but batch_decode skip_special_tokens behavior and empty-transcription generation after align_special_tokens are different code paths." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Non-persistent-buffer junk and custom model initialization are distinct regressions." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Different models and different loading failure modes." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Torch dynamo grouped_mm tracing and non-template-node compilation are unrelated failures." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer add_special_tokens conflict and Qwen3Moe FineGrainedFP8Config loading are unrelated." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Broad gguf_file/from_pretrained regression and a model-specific Qwen2.5-GGUF v5 failure are not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "FineGrainedFP8Config loading and PagedAttentionCache linear_attention crash are different issues." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "device_map/offload dequantization and Qwen2.5-GGUF loading failures are unrelated." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Qwen3.5 hidden-states behavior and Qwen2.5-VL rope-index scaling are different regressions." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Molmo tied-weights attribute error and tokenizer loading failure for EMBEDDIA/est-roberta are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Missing lm_head weight tying and inconsistent serialization of tied weights are different symptoms." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer add_special_tokens conflict and notebook custom-model initialization are not the same bug." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Non-template-node compilation and GraniteMoEHybrid invalid-method calls are different code-path failures." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and MIMI batching/padding-mask mismatch are separate issues." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization breakage and non-persistent-buffer junk are distinct regressions." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "A model-specific load failure and a tokenizer conflict are different failure surfaces." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Siglip2 nonsensical outputs and OmDet-Turbo input-size mismatch are unrelated." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Generic loading noise and Mistral regex patch crashes are not the same bug." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Llava Next loading segfault and Qwen3OmniMoe video-input ValueError are different multimodal bugs." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "MIMI padding-mask mismatch and DAC forward-vs-from_latents mismatch are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "FineGrainedFP8Config failure and template-node compilation error are different problems." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook custom initialization and non-persistent-buffer junk are distinct regressions." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "ScandiBERT loading failure and Mistral tokenizer regex crash are unrelated." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Same Qwen3.5 save_pretrained regression with incorrect serialization/visual encoder keys across versions." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Physical-intelligence/fast loading failure and Mistral regex patch crash are different bugs." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Feature-extraction fbank issues and compiled flex_attention on torch >= 2.9 are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export with torch_compilable_check and OmDet processor image sizing are different issues." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Missing lm_head tie and LoRA-merge collapse with extended vocabulary are not the same regression." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL loading failure and Qwen3-MoE sliding_window behavior are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized flag regression and mmap/OOM mitigation are different concerns." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken special-argument conflict and model loading failure are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "FineGrainedFP8Config failure and init_empty_weights _is_hf_initialized argument regression are different bugs." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "T5 tokenizer add_special_tokens conflict and MobileLLM key errors are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized flag regression and Strix Halo mmap/OOM behavior are different issues." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue and granite_speech config strictness are unrelated." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The canonical issue choice is reasonable, but the writeup overstates the evidence. The summary says only three soft pairs are true duplicates, yet the verdict list explicitly accepts only one pair and rejects the others, so the conclusions and the pair-level judgments do not line up. Also, the claimed non-persistent-buffer duplicate with issue:44534 is not reflected in the soft-edge verdicts, so that part is not fully grounded in the packet. Please either soften the summary or align the verdicts with the evidence shown." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 9, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:33666", + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43421", + "issue:43425", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43646", + "issue:43792", + "issue:43818", + "issue:43856", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44479", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44811", + "issue:44829", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45542", + "issue:45663", + "issue:45812" + ], + "soft_pairs": [ + "issue:42915|issue:44589", + "issue:43611|issue:44534", + "issue:41553|issue:43582", + "issue:43317|issue:43856", + "issue:44479|issue:45325", + "issue:43425|issue:44403", + "issue:40990|issue:44811", + "issue:42175|issue:45542", + "issue:43818|issue:45357", + "issue:44462|issue:45812", + "issue:36032|issue:41720", + "issue:43421|issue:44568", + "issue:44079|issue:45663", + "issue:43792|issue:44589", + "issue:43632|issue:44534", + "issue:44403|issue:44991", + "issue:44683|issue:45020", + "issue:43482|issue:45538", + "issue:44829|issue:45479", + "issue:33666|issue:40444", + "issue:43482|issue:43525", + "issue:44291|issue:44589", + "issue:40444|issue:45325", + "issue:43377|issue:45491", + "issue:41720|issue:45081", + "issue:42175|issue:43296", + "issue:43531|issue:44291", + "issue:43611|issue:43646", + "issue:44265|issue:45072", + "issue:43632|issue:45072" + ], + "prepared_review_unit_hash": "9158ba581bd02f810c298440d936a33c5ce4137d7b91e7b79315647a2e7b4545", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36274, + "estimated_input_tokens": 9069, + "estimated_eval_tokens": 18394 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose pile of superficially similar but distinct issues, centered around Transformers v5 regressions, tokenizer/model loading quirks, and a few unrelated model-specific bugs. I do not see any soft pair that is clearly the same underlying bug/change, so I reject all soft edges.", + "confidence": 0.87, + "canonical_issue_reason": "issue:43611 is the broadest, most representative Transformers v5 regression in the set, but it is still only a theme-level anchor rather than a true duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best global representative because it captures the common \u2018Transformers v5 breaks loading\u2019 motif shared by several nearby issues, even though the actual failures differ.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Different failure modes: FineGrainedFP8Config behavior for Qwen3Moe vs missing Float8 storage lookup during loading." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Both are Transformers v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer initialization; not the same bug." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Unrelated topics: tokenizer loading error messaging for Voxtral vs Apple Silicon caching_allocator_warmup TypeError." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Both mention memory/offload style problems, but one is device_map dequantized model offload and the other is Qwen3 MoE training memory usage." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both are Qwen VL/video issues, but one is a broad video input regression and the other is a specific still-image rope index scaling bug." + }, + { + "left": "issue:43421", + "right": "issue:44403", + "accept": false, + "reason": "Special-token/post-processor runtime updates vs generic loading noise; different code paths and symptoms." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "Perplexity on GPT-OSS WikiText evaluation is unrelated to Whisper processor batch_decode skip_special_tokens handling." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both involve backend/package availability, but TensorFlow missing from torch install is not the same as tensorboard being installed without TensorFlow." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA missing temporal attention/weight sharing is unrelated to Qwen3.5 save_pretrained visual key regression." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer-related, but one ignores tokenizer.json while the other emits wrong token IDs for Granite models; different underlying bugs." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "T5 tokenizer add_special_tokens conflict is unrelated to Qwen3 auto device mapping cudaErrorAssert." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Runtime special-token post-processing update bug is distinct from add_special_tokens=True not adding BOS/EOS for a specific tokenizer in v5." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "Generic ModelOutput key assignment logic does not match Gemma-4 FSDP2 shared_kv_states reconstruction failure." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper model inference failure is unrelated to Float8 storage lookup errors." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "_is_hf_initialized flag breakage and non-persistent buffer junk are separate Transformers v5 regressions." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Unnecessary loading noise is a UX/logging issue, not the tokenizer-loading failure for EMBEDDIA/est-roberta." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and remote_code model breakage are unrelated." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "Qwen2.5-GGUF loading failure in v5 is not the same as CLIPTokenizer using an absurd model_max_length." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Flash Attention 3 causing degenerate training is different from zero-loss single-label classification behavior across models." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and Qwen2.5-VL iterable dataset multi-image failures are related only by model family, not the same bug." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Qwen2.5-GGUF loading in transformers v5 and missing pad_token_id on Llama4Config are distinct model/config regressions." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized argument handling is a different loading path than Float8 storage resolution." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "IterableDataset multiple-image finetuning failure is unrelated to Qwen2.5-VL still-image temporal position_id scaling." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "MIMI encoder batching/padding-mask bug is unrelated to Gemma3 sliding-window NaN embeddings." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 auto device mapping cuda assert and Mistral tokenizer regex patch crash are unrelated failures." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "TensorFlow backend packaging issue is unrelated to PaddleOCR-VL model loading in vLLM." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights/_is_hf_initialized are different regressions." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both mention Transformers v5 model init/loading, but base_model_prefix loading and custom model initialization are distinct concrete bugs." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export/export with torch_compilable_check is unrelated to dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "_is_hf_initialized flag handling and bfloat16 dtype mismatches are separate issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 10, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43644", + "issue:43701", + "issue:43746", + "issue:43792", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44877", + "issue:44898", + "issue:44991", + "issue:45072", + "issue:45325", + "issue:45381", + "issue:45584", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:43454|issue:44466", + "issue:43994|issue:44898", + "issue:44079|issue:44534", + "issue:45325|issue:45834", + "issue:43792|issue:43957", + "issue:42915|issue:43482", + "issue:44079|issue:45072", + "issue:40444|issue:45381", + "issue:45325|issue:45381", + "issue:43644|issue:44079", + "issue:44387|issue:44617", + "issue:43881|issue:44488", + "issue:43296|issue:45800", + "issue:44479|issue:45823", + "issue:35707|issue:40444", + "issue:44291|issue:44877", + "issue:43317|issue:43873", + "issue:43606|issue:44265", + "issue:43701|issue:45325", + "issue:44186|issue:44265", + "issue:43606|issue:43819", + "issue:43262|issue:43746", + "issue:41720|issue:45823", + "issue:43526|issue:43883", + "issue:43454|issue:43550", + "issue:43377|issue:44610", + "issue:43454|issue:45072", + "issue:43377|issue:44898", + "issue:43572|issue:45759", + "issue:40990|issue:45584", + "issue:39692|issue:40444", + "issue:43881|issue:44991" + ], + "prepared_review_unit_hash": "740d414b763b6ef9e861a20a6103b5e739afe07d725ec70f4c66fea6d8cbd1ed", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37306, + "estimated_input_tokens": 9327, + "estimated_eval_tokens": 18910 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous; the only plausible duplicate pair is the Qwen2.5-VL position-id/rope-index regression. No PRs are present.", + "confidence": 0.66, + "canonical_issue_reason": "Issue 44479 is the broadest and most central Qwen multimodal regression report in the set, so it is the best umbrella issue if these Qwen vision/position-id bugs are grouped together.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44479 has the widest scope across multiple Qwen multimodal variants and is the strongest representative for the only nearby duplicate theme in this cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Both mention lm_head/tied-weights behavior, but one is a model-specific tie failure and the other is a generic serialization inconsistency; not the same concrete bug." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Different models and different failures; both are vision-model issues but not the same underlying bug." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "Unrelated regressions: ModelOutput key handling vs non-persistent buffer initialization." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Both involve multimodal position logic, but they target different models and symptoms; not enough to treat as the same bug." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper runtime failure vs meta-device loading issues for other models; different code paths." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Different loading/quantization problems affecting different model families." + }, + { + "left": "issue:44079", + "right": "issue:45072", + "accept": false, + "reason": "ModelOutput key assignment bug is unrelated to dtype mismatch inference failures." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen multimodal, but one is finetuning with multiple images and the other is a video-input position-id regression; not clearly the same bug." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": true, + "reason": "Same Qwen2.5-VL rope/position-id regression in transformers 5.3.0; still-image and video inputs appear to hit the same `get_rope_index` bug." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer corruption and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Generic CUDA OOM in a specific model is not the same as the quantization memory regression." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different model-loading failures with no clear shared root cause." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "vLLM/PaddleOCR-VL loading failure is unrelated to a torch/transformers version incompatibility report." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Qwen video-input regression and Gemma4 device mismatch are different bugs." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multimodal finetuning with multiple images." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Both are model/config loading issues, but they are different failures and different root causes." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both touch offloading/quantization, but one is a dequantized-model load failure and the other is a broad offloading complaint; not the same concrete bug." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch and torch.export failures via `torch_compilable_check` are unrelated." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint-key mismatch and Qwen2.5-VL position-id regression are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer padding/truncation crashes are unrelated to export-time `torch_compilable_check` failures." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to DAC `from_latents` vs forward discrepancies." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio processor sampling-rate defaulting and PEFT checkpoint loading are different issues." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Different models and different device-mapping failures." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to Molmo tied-weights attribute failure." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "Tied lm_head weights vs torch.compile/SDPA failure are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Missing padding-mask support in MIMI encoder is unrelated to OmDet-Turbo processor resolution mismatch." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Tied-weight serialization issue is unrelated to dtype mismatches in inference." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Different models and different image-processing bugs." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx and text_config unwrapping for composite multimodal configs are different problems." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "Perplexity anomaly on GPT-OSS is unrelated to Whisper empty-transcription generation failure." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Documentation/example errors for SigLIP2 are unrelated to Qwen2.5-VL finetuning failures." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different loading failures for different models and different failure modes." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The single accepted soft pair (45325/45381) is a reasonable Qwen2.5-VL position-id/rope-index duplicate candidate, and the other pair judgments do not overstate evidence. No PRs are present, so there is nothing mergeability-related to reject." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 11, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:36331", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43296", + "issue:43316", + "issue:43317", + "issue:43404", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43749", + "issue:43792", + "issue:43873", + "issue:43881", + "issue:44008", + "issue:44186", + "issue:44387", + "issue:44423", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45357", + "issue:45406", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45812", + "issue:45823" + ], + "soft_pairs": [ + "issue:44466|issue:45357", + "issue:43792|issue:44683", + "issue:43296|issue:44877", + "issue:43454|issue:43720", + "issue:43873|issue:45701", + "issue:41720|issue:44977", + "issue:44008|issue:45823", + "issue:45632|issue:45684", + "issue:43404|issue:45357", + "issue:34634|issue:35707", + "issue:44423|issue:45406", + "issue:44186|issue:45072", + "issue:43577|issue:43708", + "issue:35707|issue:41720", + "issue:43873|issue:44756", + "issue:44877|issue:44991", + "issue:43749|issue:44534", + "issue:42617|issue:42915", + "issue:43450|issue:45701", + "issue:43550|issue:43720", + "issue:36331|issue:42915", + "issue:44610|issue:44898", + "issue:44186|issue:44610", + "issue:36331|issue:42617", + "issue:44387|issue:45704", + "issue:44479|issue:44918", + "issue:43526|issue:43881", + "issue:42915|issue:43317", + "issue:43316|issue:44913", + "issue:43550|issue:43606", + "issue:45081|issue:45812" + ], + "prepared_review_unit_hash": "218fda107289796b30426dfbe931ea86fb90a843a6616cc40387d0d19d115a39", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37111, + "estimated_input_tokens": 9278, + "estimated_eval_tokens": 18812 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly topic-similar but not duplicate-level matches: they span unrelated bugs in offloading, quantization, tokenizer/config loading, multimodal processors, trainer APIs, and model-specific regressions. None of the soft pairs look like the same concrete bug or change, so all soft edges should be rejected.", + "confidence": 0.94, + "canonical_issue_reason": "No clear canonical issue; the cluster is heterogeneous and the soft pairs are only topical similarities, not duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "No single best issue for dedup triage; 43873 is broad, but it is still a distinct offloading/quantization bug rather than a representative duplicate target for the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both mention save/tied weights, but one is about v5 serialization of lm_head.weight and the other is Qwen3.5 visual encoder key persistence; different bugs and code paths." + }, + { + "left": "issue:43792", + "right": "issue:44683", + "accept": false, + "reason": "Whisper runtime failure vs torch>=2.9 flex_attention compilation failure; unrelated root causes." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "Different models and failures: PaddleOCR-VL load in vLLM vs strict config blocking granite_speech." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Both are model-loading issues, but AyaVision lm_head tying and BitNet packed-weight unpacking are distinct mechanisms." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Offloading/quantization regression vs tokenizer/version behavior change; not the same bug." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3 auto device-map CUDA assert and Qwen3.5 flash-attention generation regression are different failures." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Different model families and errors: Gemma3n forward name collision vs Gemma4 PLE device mismatch." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collision for trust_remote_code is unrelated to read-only permission propagation in save_pretrained." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Mistral3 tied-weight bug vs Qwen3.5 visual encoder save regression; no shared code path." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "Voice preset handling in BarkProcessor and generation with inputs_embeds/past_key_values are separate issues." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Different processors and failures in serve: Qwen3.5 continuous batching vs Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer padding/truncation crash vs dtype mismatch during bfloat16 inference; unrelated." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "BLIP2 dtype loading problem vs Trainer max_steps recalculation on resume; different subsystems." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation with embeddings/past KV is unrelated to Qwen3 device mapping CUDA asserts." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both involve memory/offload concerns, but one is quantization offloading behavior and the other is mmap on Strix Halo; not the same bug." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config rejection for granite_speech is unrelated to tokenizer loading failure for est-roberta." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU RAM efficient loading regression and non-persistent buffer junk fill are different loading bugs." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "3d_parallel.py execution failure and Qwen3Moe FineGrainedFP8Config failure are distinct." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video processor batching shape bug vs tokenization regression; no overlap in concrete bug." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to packed-weight unpacking during accelerate loading in BitNet." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Trainer compute_loss API mismatch vs Qwen3Moe FP8 config failure; unrelated." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both touch image preprocessing sizes, but the models and root causes differ: OmDet-Turbo processor output size vs Perceiver interpolation behavior." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Both are preprocessing/shape problems, but one is a tokenizer crash and the other is image resolution mismatch in a different model." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "CustomTrainer signature change and 3d_parallel.py runtime failure are unrelated." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Increased int4 CUDA reserved memory in Transformers 5.x is not the same as T5 using apex.FusedRMSNorm with a leak." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Qwen VL video-input regression and Qwen3.5 SFT input-embedding unpacking failure are different code paths." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug and glm-4v-9b loading failure are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "FP8 config failure for Qwen3Moe and device_map auto dequantized-model offload failure are distinct loading issues." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy and GPTNeoXConfig rotary_pct reload regression are different config bugs." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Bamba compile/SDPA issue and Bark small CPU-offload device mismatch are unrelated." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Mistral tokenizer regex patch crash and Granite token-ID regression are separate tokenizer bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 12, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30064", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43322", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43782", + "issue:43873", + "issue:43927", + "issue:44062", + "issue:44186", + "issue:44361", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44671", + "issue:44743", + "issue:44779", + "issue:44898", + "issue:44991", + "issue:45059", + "issue:45072", + "issue:45161", + "issue:45357", + "issue:45406", + "issue:45464", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45859" + ], + "soft_pairs": [ + "issue:41720|issue:43322", + "issue:40990|issue:45701", + "issue:43295|issue:45701", + "issue:41720|issue:45161", + "issue:43531|issue:43572", + "issue:44671|issue:44743", + "issue:43421|issue:45812", + "issue:41720|issue:42617", + "issue:36010|issue:42617", + "issue:43540|issue:43782", + "issue:44186|issue:44361", + "issue:45406|issue:45464", + "issue:43421|issue:45701", + "issue:30064|issue:34634", + "issue:44492|issue:44509", + "issue:44779|issue:45812", + "issue:42915|issue:43322", + "issue:43606|issue:43720", + "issue:43388|issue:45059", + "issue:43550|issue:43653", + "issue:44514|issue:44545", + "issue:43531|issue:45759", + "issue:43606|issue:43653", + "issue:43421|issue:43927", + "issue:34567|issue:35707", + "issue:44368|issue:45357", + "issue:44451|issue:44991", + "issue:45759|issue:45859", + "issue:43873|issue:45704", + "issue:44062|issue:44451", + "issue:44898|issue:45072" + ], + "prepared_review_unit_hash": "45986dde68a6e305ae9354a62d9aa220ed2e20b911220f1aa280020e0bdc56fa", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36950, + "estimated_input_tokens": 9238, + "estimated_eval_tokens": 18732 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a heterogeneous mix of unrelated Transformers bug reports spanning tokenizers, processors, generation, offloading, and model-specific regressions. The only clear duplicate pair is the two identical Qwen2_5_VLProcessor.apply_chat_template crash reports.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical duplicate target emerges from the cluster: the issues cover many unrelated models and code paths, with only one exact duplicate pair present.", + "canonical_pr_reason": null, + "best_issue_reason": "If a representative issue must be chosen, issue 43873 is the broadest and most active report, but it is still not a true umbrella duplicate for the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Different failures on different paths/models: Qwen3 auto device mapping cuda assert vs Llava Next load-time segfault." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Both mention tokenization/version regressions, but one is a perplexity regression and the other is a general tokenization change report; not the same bug." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Custom processor.tokenizer access and image passing regression is a different processor API break than the generic tokenization-change report." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Different Qwen3-related generation/distribution problems; one is auto device mapping, the other is tensor-parallel behavior." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Unrelated bugs: Qwen3-MoE sliding window behavior vs StableLmConfig missing pad_token_idx." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "Different model/code-path regressions: CamemBERT masked LM output vs Qwen recurrent cache state reset." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Both concern tokenization internals, but one is runtime special-token post-processing and the other is Granite token IDs; different underlying defects." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Device-mapping CUDA assert and a 3d_parallel.py runtime failure are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to the 3d_parallel.py execution issue." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Both involve Qwen multimodal models, but one is video-input processing and the other is from_pretrained weight_only loading; different bugs." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Tokenizer crashes on NER/padding vs AttributeError on MLuke tasks are distinct model-specific failures." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Gemma4Processor _tokenizer crash in serve is unrelated to Qwen3.5 streaming inference failures." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Runtime special-token post-processor updates are not the same as the broader tokenization-version regression report." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Image processor void segmentation maps and Bark voice_preset are unrelated processor bugs." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A documentation typo and stale docs about removed pipeline tasks are related only by docs, not the same issue." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they affect different model families and likely different root causes." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Llava Next segfault are different model loading/runtime problems." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Both touch offloading/loading, but one is CPU offload device mismatch and the other is packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Metric gathering label-drop bug and SAM3 text/box behavior are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Torch.compile SDPA failure and BigBirdTokenizer special-token decode bug are unrelated." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Exact duplicate: same title, same method, same crash condition on batched input with padding=False." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to AutoModelForCausalLM.from_config not unwrapping text_config." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Device mismatch during CPU offload and tokenizer special-token registration are unrelated bugs." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Runtime special-token update failure is not the same as DiaConfig losing custom token IDs after save/load." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token-count tracking and progressive generation with inputs_embeds/past_key_values are unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "A config warning about tie_word_embeddings is unrelated to incorrect visual encoder keys in save_pretrained." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-load regressions, but they target different models and there is no evidence of the same root cause." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Composite multimodal config unwrapping and CPU-offload rotary embedding compatibility are different Qwen 3.5 bugs." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantized offloading problems and a T5 apex memory leak are unrelated." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "AddedToken keyword collision and ScandiBERT loading failure are unrelated tokenizer issues." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver interpolation failure and bfloat16 dtype mismatch in SwitchTransformers/TimmWrapperModel are different code paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the cluster is broadly heterogeneous, and the one exact duplicate pair (issue:44514 / issue:44545) is directly supported by identical titles. The soft-edge verdicts are conservative and generally justified by distinct model/path or bug descriptions, without overclaiming broader duplicate relationships." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 13, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30064", + "issue:33666", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:42886", + "issue:42915", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43596", + "issue:43618", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43819", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44843", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:45042", + "issue:45081", + "issue:45183", + "issue:45356", + "issue:45381", + "issue:45479", + "issue:45588", + "issue:45704", + "issue:45759", + "issue:45859" + ], + "soft_pairs": [ + "issue:41720|issue:43746", + "issue:44987|issue:45042", + "issue:43531|issue:44589", + "issue:33666|issue:35707", + "issue:43421|issue:43653", + "issue:45588|issue:45759", + "issue:42886|issue:44843", + "issue:43381|issue:43844", + "issue:44918|issue:44936", + "issue:39692|issue:44610", + "issue:43421|issue:44186", + "issue:43525|issue:43531", + "issue:44625|issue:45479", + "issue:45704|issue:45859", + "issue:43782|issue:45381", + "issue:45081|issue:45356", + "issue:34634|issue:41720", + "issue:43994|issue:44671", + "issue:39692|issue:43873", + "issue:43381|issue:45704", + "issue:42915|issue:45759", + "issue:43596|issue:44220", + "issue:43540|issue:44008", + "issue:43618|issue:43697", + "issue:44220|issue:44661", + "issue:45183|issue:45479", + "issue:44077|issue:44625", + "issue:30064|issue:36010", + "issue:43720|issue:43819" + ], + "prepared_review_unit_hash": "cd067ad4395f82def11681ba1362f2d63c3bb29c67a705e871cc75d4426bf217", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36553, + "estimated_input_tokens": 9139, + "estimated_eval_tokens": 18534 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a very heterogeneous set of issues with only superficial keyword overlap (Qwen, tokenizers, offload, quantization, multimodal processors). I do not see any true duplicate pair here, so no soft edge should be merged.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Both involve model loading/configuration, but they are different models and failures: Qwen3 auto device mapping CUDA assert vs GraniteSpeech PEFT local checkpoint loading." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Unrelated bugs: loading physical-intelligence/fast on newer transformers vs PIL image processors incorrectly requiring torchvision." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Different problems and code paths: Qwen3-MoE sliding_window behavior vs missing Float8 storage type during deserialization." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Both are training-related, but one is Qwen2-VL multi-GPU training and the other is progressive generation with inputs_embeds/past_key_values; not the same bug." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both concern tokenizer internals, but one is runtime special-token post-processor updates and the other is BigBirdTokenizer mask token registration/empty decode output." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Different subsystems and failures: flash_attention sink-less model handling vs from_config not unwrapping text_config for Qwen multimodal configs." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": false, + "reason": "Both relate to offline/cache behavior, but one is tokenizer cache loading in HF_HUB_OFFLINE and the other is an unconditional model_info() call in _patch_mistral_regex." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Both mention training/eval or gradient behavior, but one is gradient checkpointing in eval mode and the other is gradient explosion with HfDeepSpeedConfig + ZeRO-3." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different failures: Qwen3.5 input-embeddings unpacking with TRL SFT trainer vs trainer.evaluate() failing after trainer.train()." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Similar multimodal/documentation flavor, but one is SigLIP2 doc example/model-processor mismatch and quantization errors; the other is OmDet-Turbo processor/model image-size mismatch." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Both are tokenizer bugs, but the concrete issues differ: dynamic special-token post-processing vs LayoutLMv2Tokenizer crashes on NER inputs and batching." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Both are Qwen-related config issues, but pad_token_id missing in Llama4Config is unrelated to Qwen3-MoE sliding_window behavior." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Both touch classification config propagation, but one is Qwen3.5 num_labels wiring and the other is zero-loss behavior for single_label_classification with num_labels=1 across sequence-classification models." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "Different memory/offload problems: T5 silently using apex.FusedRMSNorm vs Qwen3_5MoeTextRotaryEmbedding not being CPU-offload compatible." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Both concern Qwen/VL model loading or behavior, but one is weight_only loading error and the other is incorrect video vision_position_ids in qwen2.5-vl." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both involve Mistral-regex-related tokenizer behavior, but one is a crash on backend_tokenizer access and the other is a Kimi-K2.5 regression with incorrect codec handling and warning text." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "Completely different models and bugs: BarkProcessor voice_preset handling vs Qwen3 auto device mapping CUDA assert." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Both are model behavior regressions, but SigLIP2 nonsensical outputs and CamemBERT masked-LM predictions are unrelated code paths." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "Both mention quantization/loading issues only at a very high level; SigLIP2 doc/example bugs are not the same as quantization offloading not working as expected." + }, + { + "left": "issue:43381", + "right": "issue:45704", + "accept": false, + "reason": "Both involve training/runtime behavior, but gradient checkpointing in eval mode is unrelated to T5 using apex.FusedRMSNorm and its memory leak." + }, + { + "left": "issue:42915", + "right": "issue:45759", + "accept": false, + "reason": "Both are Qwen-family config/runtime issues, but FineGrainedFP8Config failure and from_config not unwrapping text_config are distinct bugs." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Different failure modes: Deepspeed ZeRO-3 init with BertModel index error vs _torch_extract_fbank_features() issue." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Both are multimodal model forward-path bugs, but one is Qwen3OmniMoe video input validation and the other is Gemma 3n variable-name collision causing audio_mel_mask AttributeError." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "A broad similarity around model outputs, but CLIPOutput attentions assignment and RTDetrV2 output drift in v5 are different models and regressions." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Unrelated tokenizer/audio issues: fbank feature extraction vs add-new-model-like failing for TOKENIZER_MAPPING_NAMES." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Generic validation logic vs a specific classification-loss degeneracy; same area, but not the same bug or fix." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Patchtsmixer post_init policy and Qwen3.5 num_labels propagation are unrelated model/config issues." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Image processor void segmentation-map handling is unrelated to the GenerationMixin import error." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Different models and mechanisms: BitNet packed-weight unpacking during accelerate loading vs DAC.from_latents missing STE mismatch." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 14, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30064", + "issue:36331", + "issue:39692", + "issue:42915", + "issue:43295", + "issue:43322", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43653", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43825", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44448", + "issue:44479", + "issue:44485", + "issue:44488", + "issue:44509", + "issue:44561", + "issue:44671", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45381", + "issue:45584", + "issue:45685", + "issue:45834" + ], + "soft_pairs": [ + "issue:43335|issue:43756", + "issue:43653|issue:43720", + "issue:43716|issue:44008", + "issue:42915|issue:43746", + "issue:43295|issue:45834", + "issue:43746|issue:45381", + "issue:43550|issue:45072", + "issue:43746|issue:43873", + "issue:43550|issue:43819", + "issue:44186|issue:44898", + "issue:44843|issue:45081", + "issue:43531|issue:43643", + "issue:44062|issue:44488", + "issue:43643|issue:44877", + "issue:43421|issue:44811", + "issue:43577|issue:43818", + "issue:43540|issue:45381", + "issue:43653|issue:43819", + "issue:44448|issue:44671", + "issue:43782|issue:44977", + "issue:45584|issue:45834", + "issue:43322|issue:45685", + "issue:44561|issue:45020", + "issue:43825|issue:43994", + "issue:44821|issue:45084", + "issue:44485|issue:44509", + "issue:39692|issue:45834", + "issue:30064|issue:36331", + "issue:44479|issue:45834" + ], + "prepared_review_unit_hash": "94b7d9204e910a006bf514aba686bc3b806076cf09a34bcdcd79c5cd016ae096", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36627, + "estimated_input_tokens": 9157, + "estimated_eval_tokens": 18570 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly heterogeneous; the only near-overlap is around Mistral regex patching, but the reported failures are different enough that I would not merge them. No PRs are present.", + "confidence": 0.41, + "canonical_issue_reason": "If a single anchor is needed, issue #45020 is the broadest umbrella-style report in the set (remote_code regressions) and is open, but the cluster does not really form a true duplicate group.", + "canonical_pr_reason": null, + "best_issue_reason": "#45020 is the best global issue anchor only because it is the broadest and most central open regression report among otherwise unrelated issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Different models and different bugs: sparse-layer config construction vs RoPE-layer dropping." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token registration vs BitNet packed-weight loading; unrelated failure modes." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Different multimodal code paths: image preprocessor dtype mismatch vs Gemma3n forward variable collision." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "FP8 config failure in Qwen3Moe is unrelated to GraniteSpeech PEFT checkpoint loading." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Processor/tokenizer regression in one model versus OCR index error in another." + }, + { + "left": "issue:43746", + "right": "issue:45381", + "accept": false, + "reason": "Checkpoint loading with adapters is unrelated to Qwen video position-id bugs." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Different backends and problems: torch.compile SDPA issue vs bfloat16 dtype mismatch." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "Local checkpoint loading with PEFT adapters is not the same as quantization offloading behavior." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Unrelated models and code paths; compile/SDPA bug does not match DAC latent mismatch." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer padding/truncation crash is unrelated to Perceiver image classification resolution handling." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both touch _patch_mistral_regex, but one is offline network access and the other is an AttributeError on tokenizer structure; not the same concrete bug." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to trust_remote_code config field loss." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken constructor misuse is not the same as loading a specific model failing." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config loading, but one is missing fields with trust_remote_code and the other is strict GraniteSpeech config rejection." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Special-token post-processor updates and Whisper batch_decode skip_special_tokens are different tokenizer behaviors." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "Blip2 dtype propagation and Video-LLaVA temporal attention/shared weights are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both are video-related, but they affect different Qwen model families and distinct bugs." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "Tokenizer special-token registration and DAC from_latents/forward mismatch are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Different model regressions with different outputs; not the same issue." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Weight-only loading error for Qwen3VL is unrelated to flash-attention generation behavior in Qwen3.5." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription generation and Kosmos2.5 long-OCR index error are different models and failures." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Segfault in Llava Next loading is unrelated to MPS histogram support for MoE int tensors." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Removal of is_torch_fx_available is one specific cause; #45020 is a broad remote_code regression report, not the same concrete bug." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "Pipeline task messaging regression is unrelated to SigLIP2 inference producing nonsensical results." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to v5 docs still mentioning removed tasks." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "SigLIP2 doc example errors are unrelated to Kosmos2.5 OCR indexing." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Image segmentation-map processing bug is unrelated to CustomTrainer compute_loss argument breakage." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Qwen video regression across multiple models is unrelated to Kosmos2.5 OCR input length handling." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "Loading AutoImageProcessor from URL and non-template-node compilation errors are different problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 15, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:34634", + "issue:36010", + "issue:42175", + "issue:43262", + "issue:43329", + "issue:43404", + "issue:43452", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43638", + "issue:43644", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43746", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:44060", + "issue:44186", + "issue:44368", + "issue:44442", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44811", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45406", + "issue:45459", + "issue:45538", + "issue:45600", + "issue:45701", + "issue:45803" + ], + "soft_pairs": [ + "issue:43825|issue:43827", + "issue:44186|issue:44442", + "issue:43606|issue:45072", + "issue:43577|issue:43582", + "issue:34634|issue:36010", + "issue:44805|issue:44936", + "issue:43452|issue:44991", + "issue:42175|issue:45081", + "issue:44610|issue:45072", + "issue:43720|issue:45072", + "issue:44060|issue:44368", + "issue:45081|issue:45406", + "issue:44671|issue:45701", + "issue:43404|issue:43782", + "issue:43650|issue:43906", + "issue:43582|issue:44857", + "issue:43262|issue:43819", + "issue:43526|issue:43697", + "issue:45459|issue:45803", + "issue:45084|issue:45538", + "issue:43644|issue:43749", + "issue:43329|issue:45600", + "issue:43742|issue:45020", + "issue:43653|issue:44912", + "issue:43638|issue:44936", + "issue:43746|issue:44811" + ], + "prepared_review_unit_hash": "0cc2bcc817561ab74b8345494bc878a32693dfc3643eb7b0314fc22a5e084640", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35264, + "estimated_input_tokens": 8816, + "estimated_eval_tokens": 17888 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous; the soft-similarity pairs mostly share only broad Transformers-theme vocabulary and do not look like true duplicates.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue: the cluster spans unrelated bugs across tokenization, loading, precision, audio, multimodal, training, and CI paths.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to pick one representative issue, issue 45020 is the broadest open report, but it is still too general to anchor the rest of the cluster as duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Related v5/pipeline theme, but one is an error-message bug and the other is stale documentation; not the same underlying defect." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer problems, but they affect different tokenizers and different failure modes." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Both mention inference mismatches, but they involve different models and different code paths (CPU offload vs bfloat16 dtype handling)." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Unrelated issues: BLIP2 dtype loading versus an Apple Silicon allocator TypeError." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "Different subsystems and failures: BarkProcessor voice preset versus a transformers import error." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Different bugs: tensor/mask shape mismatch versus training-to-evaluation state transition failure." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both concern loading, but one is gguf_file handling and the other is tokenizer loading for a specific model; not the same bug." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "No shared underlying defect: backend dependency packaging versus Mistral regex patching." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Different problem domains: processor image size mismatch versus dtype mismatch during inference." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Different loading bugs with different models and causes; not mergeable as one PR-worthy fix." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Same general Qwen family, but one is a bad tied-weights warning path and the other is a user-facing config warning during LoRA fine-tuning." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both are AttributeErrors during loading, but on different objects and different code paths." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "Only loosely related to tokenization changes; one is CamemBERT MLM output regression and the other is a general tokenization change report." + }, + { + "left": "issue:43404", + "right": "issue:43782", + "accept": false, + "reason": "Different model families and different loading failures; too broad to be duplicates." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "No meaningful overlap beyond being issue reports; one is a placeholder title and the other is a reproduction of another bug." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Allocator TypeError and CUDA AMP image-loss crash are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Both are audio-related, but one is sampling-rate default handling and the other is a DAC latent/forward mismatch." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Different components: Beit image processor label reduction versus RTDetrV2 output regression." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both involve overly broad exception handling, but they are in different modules and hide different classes of failures." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "No duplicate signal: template compilation error versus CLIP model_max_length configuration." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both are loading/initialization regressions, but one is non-persistent buffer filling and the other is FSDP RAM-efficient loading." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Unrelated CI/runtime issues in different files and code paths." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "A specific key error on one model is not the same as the broader remote_code compatibility regression." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Tokenizer special-token registration bug versus MXFP4 quantization fallback; different defects." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Different training/evaluation failures with different triggers and stack paths." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "PEFT local-checkpoint loading and Whisper batch_decode skip_special_tokens are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 16, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:34567", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43643", + "issue:43645", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44291", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44811", + "issue:44849", + "issue:44912", + "issue:44977", + "issue:45042", + "issue:45356", + "issue:45357", + "issue:45488", + "issue:45701", + "issue:45759", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:44589|issue:45042", + "issue:43854|issue:44977", + "issue:38175|issue:44610", + "issue:43526|issue:44554", + "issue:39692|issue:44912", + "issue:36010|issue:43645", + "issue:34634|issue:36331", + "issue:43819|issue:43927", + "issue:43257|issue:43329", + "issue:43454|issue:43577", + "issue:43720|issue:44610", + "issue:43550|issue:44912", + "issue:44568|issue:45488", + "issue:43749|issue:44291", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:44568|issue:45356", + "issue:43643|issue:45759", + "issue:36010|issue:36331", + "issue:44849|issue:45701", + "issue:34567|issue:40990", + "issue:43329|issue:43450", + "issue:43329|issue:44479", + "issue:43606|issue:45859", + "issue:43257|issue:43931", + "issue:43697|issue:45357", + "issue:45823|issue:45859", + "issue:44291|issue:45042", + "issue:41720|issue:43540", + "issue:42915|issue:43742" + ], + "prepared_review_unit_hash": "84a430744d9ee1bb61d0354e2880b2bc9f0c93dd4363a56b17b515441b5c7746", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36931, + "estimated_input_tokens": 9233, + "estimated_eval_tokens": 18722 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: most pairs are only loosely similar at the subsystem level (tokenizers, multimodal processors, loading, device/offload issues) but do not look like the same underlying bug. I would keep them separate.", + "confidence": 0.34, + "canonical_issue_reason": "issue:45701 is the broadest umbrella in the set for version-dependent tokenization regressions and is the least specific/common representative if one issue must anchor the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45701 is the best global representative because it is broad, user-facing, and closer to a cross-cutting regression than the model-specific or one-off implementation bugs here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Different subsystems and symptoms: float8 storage loading vs PIL backend requiring torchvision." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Both involve model usage, but the failures are different models and different paths (loading tests vs flash-attention generation)." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Vision model output issue vs processor input-size mismatch; not the same bug." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "Beit label reduction bug is unrelated to an MPS attention correctness issue." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Doc/example errors for SigLIP2 do not match an MXFP4 quantization fallback bug." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "Both touch v5 compatibility, but one is an import error and the other is Jupyter custom-model initialization." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice preset and Trainer compute_loss signature are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent reconstruction mismatch is unrelated to DiaConfig token-ID persistence." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MoE loading with accelerate/deepspeed is unrelated to a multimodal token-counting video-branch bug." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "Weight tying in AyaVision and dtype propagation in Blip2 are different defects." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Packed-weight loading in BitNet is unrelated to OmDet-Turbo processor image-size output." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "torch.compile/SDPA failure is not the same as MXFP4 quantization fallback." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different tokenizer behaviors and likely different code paths." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Accelerate/FSDP loading breakage is different from the unexpected _is_hf_initialized argument issue." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE is unrelated to the torchvision backend requirement regression." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sample-rate defaulting and Whisper batch_decode skip_special_tokens are separate processor bugs." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer regressions: special-token insertion vs codec/warning handling." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Missing fields from AutoConfig with trust_remote_code is not the same as not unwrapping text_config in AutoModelForCausalLM.from_config." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "GenerationMixin import failure and compute_loss kwarg mismatch are unrelated trainer/API regressions." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Hidden-state output bug in Qwen3.5 is not the same as a broad tokenization-change regression." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "TrainerState token-count tracking and GPT-OSS perplexity are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Video token counting and batched video processor output shape are related only broadly; not the same concrete bug." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Both mention video paths, but one is undefined helpers in token counting while the other is a model-family regression in v5.3.0." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Both are CPU-offload/device-placement issues, but they affect different models and code paths." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE weight conversion and Qwen3-VL weight-shape mismatch are different loading failures." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetrV2 output differences and Qwen3.5 save_pretrained key mismatches are unrelated regressions." + }, + { + "left": "issue:45823", + "right": "issue:45859", + "accept": false, + "reason": "Both involve offload/device mapping, but Gemma4 PLE forward mismatch is not the same as Qwen3_5Moe rotary embedding CPU-offload incompatibility." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "init_empty_weights type handling and PIL backend torchvision dependency are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert and Qwen3OmniMoe video input ValueError are different failures." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure is unrelated to MobileLLM key loading error." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 17, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:33357", + "issue:34567", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43452", + "issue:43493", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43646", + "issue:43696", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43824", + "issue:43906", + "issue:43927", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44560", + "issue:44737", + "issue:44756", + "issue:44792", + "issue:44821", + "issue:44898", + "issue:44912", + "issue:44964", + "issue:44987", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45137", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45538", + "issue:45588", + "issue:45823" + ], + "soft_pairs": [ + "issue:43317|issue:45538", + "issue:43452|issue:43582", + "issue:33357|issue:34567", + "issue:44987|issue:45538", + "issue:42915|issue:44821", + "issue:43927|issue:44912", + "issue:44479|issue:45381", + "issue:42915|issue:45538", + "issue:43257|issue:43756", + "issue:43540|issue:44560", + "issue:43540|issue:44479", + "issue:43257|issue:43696", + "issue:43577|issue:45072", + "issue:45137|issue:45405", + "issue:38175|issue:44898", + "issue:44062|issue:44991", + "issue:44737|issue:45588", + "issue:43742|issue:44291", + "issue:43540|issue:45823", + "issue:43906|issue:45381", + "issue:43646|issue:43749", + "issue:44062|issue:45081", + "issue:43643|issue:45375", + "issue:43749|issue:44756", + "issue:34567|issue:36331", + "issue:36010|issue:42175", + "issue:43493|issue:43994", + "issue:42175|issue:43824", + "issue:43452|issue:44488", + "issue:44291|issue:44821", + "issue:44792|issue:44964" + ], + "prepared_review_unit_hash": "3702f772e27f08fc3af1d30729de03ebf402f749558772d660e88e0d886a1a5d", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36471, + "estimated_input_tokens": 9118, + "estimated_eval_tokens": 18492 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous bag of unrelated model-loading, tokenizer, video, quantization, and training issues. Only two soft pairs look like true duplicates: the Qwen2.5-VL video regression pair and the SigLIP2 discrepancy pair.", + "confidence": 0.93, + "canonical_issue_reason": "No canonical issue: the items span different bugs and subsystems, so one issue would not represent the cluster well.", + "canonical_pr_reason": "No PRs are present in this cluster.", + "best_issue_reason": "No single issue is a strong global anchor; the cluster is too heterogeneous, with only a couple of genuine duplicate pairs.", + "best_pr_reason": "No PRs are present in this cluster.", + "soft_edge_verdicts": [ + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Different bugs: device_map/offload dequantized-model loading vs CLIPTokenizer model_max_length behavior." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Different code paths: GGUF AutoTokenizer/AutoModel loading vs Apple Silicon mmap warmup TypeError." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Unrelated failures: MacOS bus error on CLIP vs TrainerState token-count bookkeeping." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Different issues: a model-loading failure for physical-intelligence/fast vs tokenizer max length setting." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Different subsystems: Qwen3Moe FP8/quantization failure vs loading AutoImageProcessor from URL." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "Different bugs: DiaConfig save/load token ID loss vs MXFP4 quantization fallback." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Same underlying regression: both report the v5.3.0 Qwen2.5-VL video-input/vision_position_ids bug; 45381 is a narrower symptom of 44479." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated topics: Qwen3Moe fine-grained FP8 failure vs CLIPTokenizer max-length behavior." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different model families and failures: Qwen3 MoE weight conversion vs Smollm3 RoPE-layer mismatch." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-input errors, but on different Qwen model paths with different failure modes." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Different model families: Qwen3OmniMoe video processing error vs Qwen2.5/Qwen3 video-input regression." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Different bugs: Qwen3 MoE loading/weight-conversion issue vs GPT-oss-20b OOM." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both are dtype-related, but they affect different models and different failure mechanisms." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "Completely unrelated: ZeRO3 deque error vs a dependency-version bump complaint." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Different models and symptoms: SigLIP2 zero probabilities vs Perceiver non-default-resolution failure." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Tokenizer-loading issues, but different root causes and models; not the same bug." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "Different subsystems: XLNet positional encoding device placement vs flash-attention sink-less model crash." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "Different loading failures: MobileLLM key error vs init_empty_weights/_is_hf_initialized TypeError." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Different model-specific forward-path bugs in different multimodal architectures." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "Isolated reproduction of another issue vs a Qwen2.5-VL video-input regression; not the same artifact." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Different problems: custom model initialization breakage vs FSDP CPU RAM efficient loading." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizers, but the actual errors and code paths are different." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Related config-field loss theme, but one is generic trust_remote_code behavior and the other is a specific Qwen config field dropped by @strict; not clearly the same bug." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Different memory/loading issues: FSDP CPU RAM efficient loading vs disabling mmap on Strix Halo." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Different Trainer API issues: token count tracking vs unexpected compute_loss keyword argument." + }, + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "Unrelated: GenerationMixin import regression vs TensorFlow backend packaging." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Same underlying SigLIP2 problem: 43994 describes the user-visible bad outputs caused by the HF-vs-JAX discrepancy in 43493." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Different import/package issues: TensorFlow backend omission vs missing Qwen2.5-VL class export." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Different model loading failures: GGUF handling vs sleng-bert loading." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "Different failures: init_empty_weights argument mismatch vs AutoImageProcessor URL loading." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Different multimodal model issues with no shared code path." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is conservative and grounded in the packet: it correctly reflects a heterogeneous cluster and only elevates the two soft pairs that are marked as true duplicates in the packet (44479/45381 and 43493/43994). The non-duplicate verdicts are also appropriately cautious, with no obvious overstatement of evidence. No PRs are present, so that part is consistent." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 18, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:34689", + "issue:41762", + "issue:42175", + "issue:43295", + "issue:43452", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43819", + "issue:44466", + "issue:44484", + "issue:44514", + "issue:44561", + "issue:44568", + "issue:44589", + "issue:44625", + "issue:44704", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44938", + "issue:44977", + "issue:45005", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45600", + "issue:45823" + ], + "soft_pairs": [ + "issue:43526|issue:45479", + "issue:28282|issue:34689", + "issue:45042|issue:45081", + "issue:43756|issue:45325", + "issue:43742|issue:44589", + "issue:45405|issue:45600", + "issue:43697|issue:45216", + "issue:43531|issue:44821", + "issue:44484|issue:44704", + "issue:44514|issue:45381", + "issue:28282|issue:29127", + "issue:43643|issue:44561", + "issue:44625|issue:44877", + "issue:43582|issue:44977", + "issue:43720|issue:44898", + "issue:42175|issue:44938", + "issue:43452|issue:43577", + "issue:41762|issue:44936", + "issue:44514|issue:45290", + "issue:43452|issue:44843", + "issue:44466|issue:45005", + "issue:43295|issue:45356", + "issue:43819|issue:44811", + "issue:43653|issue:44568", + "issue:44936|issue:45823", + "issue:24643|issue:29127" + ], + "prepared_review_unit_hash": "9d58f481c37cef9a89a806474f136abdb94b1e0bdd1f40f8e84edbe561cdd054", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35360, + "estimated_input_tokens": 8840, + "estimated_eval_tokens": 17936 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All suggested soft-edge pairs are false positives: they share broad keywords or subsystems, but not the same concrete bug or change. No canonical duplicate issue/PR emerges from this set.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Different bugs in sequence-label handling vs classification loss behavior; same label terminology only." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Generic PyTorch import failure vs a specific Llama 3.2 Vision model-loading regression." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "One is an unwanted torchvision dependency; the other is an AttributeError in Mistral regex patching." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both involve positional encoding, but they affect different models and different code paths." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "KeyError while loading a model vs a float8 storage lookup failure; unrelated failure modes." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "Dependency version bump vs stale auto-mapping references; not the same bug." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Different regressions: RTDetr output drift versus Qwen3.5 checkpoint serialization." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE vs loading AutoImageProcessor from a URL." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "Save-pretrained shard-size discussion vs missing kwargs passthrough in AutoProcessor." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Different Qwen2.5-VL bugs: chat-template batching crash vs video rope-index scaling." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "ImportError for missing PyTorch is unrelated to LayoutLMv3 error-message clarity." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both touch trust_remote_code, but one loses config fields while the other removes a helper used by remote models." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Config num_labels propagation bug vs overly strict loading of granite_speech config." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon warmup TypeError vs Qwen3.5 flash-attention generation bug; unrelated." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "Packed-weight loading issue in BitNet vs Perceiver image-classification resolution handling." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Backend dependency packaging problem vs Python 3.14 import/load failure." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "gguf_file tokenizer/model loading breakage vs BLIP2 dtype propagation bug." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed ZeRO-3 loading error vs trainer.evaluate() failing after train()." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both involve apply_chat_template, but one is batched padding behavior and the other is assistant tool-call content handling." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "gguf_file loading failure vs offline mistral-regex patch calling model_info()." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but one is device-dependent lm_head serialization and the other is translation-model weight-tie issues." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Processor tokenizer access regression vs Kimi-K2.5 codec/mistral-regex warning regression." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC latent decoding mismatch vs Whisper batch_decode special-token handling." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Different tokenizer special-token bugs affecting different tokenizers and symptoms." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "Trainer evaluation failure after training vs Gemma4 device-map forward mismatch." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed weight-shape runtime error is unrelated to LayoutLMv3 box-information messaging." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 19, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:30064", + "issue:32090", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:38175", + "issue:41720", + "issue:43122", + "issue:43295", + "issue:43329", + "issue:43452", + "issue:43504", + "issue:43525", + "issue:43531", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44451", + "issue:44464", + "issue:44568", + "issue:44610", + "issue:44743", + "issue:44821", + "issue:44843", + "issue:44849", + "issue:44913", + "issue:44977", + "issue:44991", + "issue:45325", + "issue:45356", + "issue:45357", + "issue:45440", + "issue:45588", + "issue:45812" + ], + "soft_pairs": [ + "issue:30064|issue:33666", + "issue:38175|issue:43295", + "issue:44361|issue:44442", + "issue:43653|issue:44361", + "issue:43577|issue:43697", + "issue:44464|issue:44743", + "issue:44843|issue:44991", + "issue:41720|issue:43906", + "issue:44977|issue:45356", + "issue:43688|issue:45440", + "issue:43531|issue:43742", + "issue:43653|issue:43927", + "issue:44464|issue:44977", + "issue:43550|issue:43927", + "issue:43577|issue:45588", + "issue:43550|issue:44361", + "issue:32090|issue:34567", + "issue:43504|issue:43550", + "issue:43504|issue:43720", + "issue:43122|issue:43906", + "issue:43504|issue:44610", + "issue:28282|issue:35141", + "issue:32090|issue:33666", + "issue:43452|issue:44451", + "issue:44849|issue:45357", + "issue:44568|issue:45812", + "issue:43742|issue:44821", + "issue:41720|issue:44464", + "issue:33666|issue:36010", + "issue:43525|issue:43572", + "issue:43756|issue:44913", + "issue:43329|issue:45325", + "issue:43688|issue:43749" + ], + "prepared_review_unit_hash": "db02144138b601cdef850b5476484b79cfd1b9bd38a69e807cb5aae09cf8d30f", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 37179, + "estimated_input_tokens": 9295, + "estimated_eval_tokens": 18846 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is a heterogeneous mix of unrelated Transformers issues across tokenizers, model/config reloads, multimodal processors, training, generation, and MoE internals. I don\u2019t see a true duplicate cluster here; the soft links are mostly superficial similarity only.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue: the cluster is not centered on one underlying bug. If a representative issue is needed, issue:45812 is the broadest recent tokenizer-regression report, but it is not a true duplicate anchor for the rest.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue:45812 is the strongest representative bug report in the set because it describes a broad, user-visible tokenizer regression affecting multiple Granite models and has the most general scope among the issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Different subsystems and failure modes: image processor segmentation-map handling vs multi-GPU training for Qwen2-VL." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Different bug classes: zero probabilities in SigLIP2 inference vs processor/tokenizer regression in custom multimodal code." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer-related, but one is an AttributeError in MLukeTokenizer tasks and the other is AutoTokenizer failing to load a specific tokenizer; not the same bug." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Unrelated tokenizer bugs: BigBird special-token registration vs MLukeTokenizer task AttributeError." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Different model families and symptoms: BLIP2 dtype casting vs RTDetrV2 output divergence." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation behavior, but one is compiled-forward chunked generation and the other is recurrent-state reset with cache; different code paths." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both concern tokenizer loading regressions, but the root causes differ: offline hub call in Mistral regex patch vs model-specific tokenizer load failure." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Too little evidence for the same bug: one is a Qwen3 auto device-mapping CUDA assert, the other is only an isolated reproduction of a different issue." + }, + { + "left": "issue:44977", + "right": "issue:45356", + "accept": false, + "reason": "Different models and defects: Qwen3.5 flash-attention generation vs Kimi-K2.5 tokenizer codec/regex regression." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-related, but the reported issues differ: auxiliary-loss normalization vs divergence from a remote implementation." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "No shared underlying bug: Qwen3-MoE sliding-window logic vs MobileLLM model-loading key error." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Different components: tokenizer special-token registration vs config save/load dropping custom token IDs." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Different failure modes and models: compiled-forward chunked generation vs flash-attention generation on Qwen3.5." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "Unrelated issues: torch.compile with SDPA in Bamba vs DiaConfig custom token IDs lost on save/load." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Different code paths: BLIP2 dtype loading vs flash_attention.py crashing on s_aux=None." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "No match beyond vague model/runtime errors; Bamba SDPA compile bug is unrelated to MLukeTokenizer task errors." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Different trainer issues: NoneType broadcast error vs TrainerState counter not updating." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Different model-loading bug vs compile/SDPA runtime bug; not the same underlying issue." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Both are model-loading related, but one is a legacy-field preset load failure and the other is packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Different problem domains: tokenization changes across versions vs Qwen3 auto device-mapping/CUDA assert." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Different models and symptoms: Beit preset loading vs OmDet-Turbo processor image-size mismatch." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "Unrelated issues: missing PyTorch dependency vs output embedding reinitialization after resizing token embeddings." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer broadcast/type issue is unrelated to Qwen2-VL multi-GPU training." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "Both are loading failures, but one is about gguf_file support and the other is a specific model load regression; not enough to treat as one bug." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Same model family but different regressions: hidden-states behavior vs incorrect visual-encoder keys on save_pretrained." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different tokenizers and different symptoms; not the same underlying bug." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Different load paths and failure types: MobileLLM key error vs AutoImageProcessor URL loading failure." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Different runtime failures: Qwen3 auto device mapping CUDA assert vs chunked generation inconsistency under compiled forward." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Unrelated Qwen2-VL training issue vs GenerationMixin import error." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Similar pattern of missing config fields, but different attributes, model families, and reload behavior; not the same bug." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Both involve rotary/RoPE config behavior, but one is about Smollm3 layer composition and the other about GPTNeoX rotary_pct reload semantics." + }, + { + "left": "issue:43329", + "right": "issue:45325", + "accept": false, + "reason": "Different multimodal bugs: undefined helpers in video token counting vs Qwen2.5-VL rope index scaling for still images." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Both affect training/loading infra, but one is MoE auxiliary-loss normalization and the other is FSDP CPU RAM efficient loading." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 20, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:36331", + "issue:39692", + "issue:43257", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43646", + "issue:43688", + "issue:43720", + "issue:43756", + "issue:43824", + "issue:43825", + "issue:43844", + "issue:43927", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44554", + "issue:44589", + "issue:44625", + "issue:44734", + "issue:44843", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45405", + "issue:45520", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43493|issue:43825", + "issue:43262|issue:43295", + "issue:43606|issue:43927", + "issue:43720|issue:43927", + "issue:28282|issue:32090", + "issue:28282|issue:33357", + "issue:43577|issue:44554", + "issue:33666|issue:36331", + "issue:39692|issue:43493", + "issue:43720|issue:44361", + "issue:43334|issue:43572", + "issue:43688|issue:45704", + "issue:43540|issue:44977", + "issue:44964|issue:45405", + "issue:44479|issue:44625", + "issue:43493|issue:43844", + "issue:43334|issue:45759", + "issue:43756|issue:45083", + "issue:45200|issue:45229", + "issue:44488|issue:44843", + "issue:43257|issue:43299", + "issue:43278|issue:43844", + "issue:43824|issue:44589", + "issue:43646|issue:44466", + "issue:45229|issue:45823", + "issue:44589|issue:45520", + "issue:43688|issue:45701", + "issue:39692|issue:43295", + "issue:43572|issue:44291", + "issue:33357|issue:33666", + "issue:43504|issue:43606", + "issue:44423|issue:44734", + "issue:43927|issue:44361" + ], + "prepared_review_unit_hash": "a7d9f99b4afff41d12d5da3763ecdeb40e3e922a326117e6106faa85c35874e4", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37970, + "estimated_input_tokens": 9493, + "estimated_eval_tokens": 19242 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly unrelated bug reports that only share broad themes like model loading, multimodal regressions, or Transformers v5 breakage. None of the soft pairs look like the same underlying bug or a mergeable duplicate PR-level change, so all soft edges are rejected.", + "confidence": 0.93, + "canonical_issue_reason": "issue:43646 is the broadest umbrella-style report here (generic Transformers 5.0 custom initialization breakage), so it is the best representative issue for this noisy cluster, even though the set is heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the most general and central issue among the candidates, making it the closest thing to a canonical representative for the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "Both are transformer/model related, but one is a SigLIP2 implementation discrepancy and the other is a pipeline error message regression; different bugs and code paths." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat-template sampling-rate handling is unrelated to the processor.tokenizer / image-to-tokenizer regression." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch for bark-small is unrelated to DiaConfig losing token IDs on save/load." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is a different failure mode from config token ID persistence." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "Missing PyTorch import and Trainer _gpu_broadcast_one NoneType error are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "AutoModel import failure is not the same as the MacOS CLIP bus error regression." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype propagation and an MPS attention correctness issue are distinct bugs." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Multi-GPU training support request is unrelated to a CustomTrainer compute_loss API break." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Documentation example mistakes are not the same as a SigLIP2 implementation mismatch with JAX." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "BitNet packed-weight loading and MLukeTokenizer task errors are different code paths and symptoms." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Qwen3-VL pad_token_id missing and StableLmConfig pad_token_idx missing are separate model/config bugs." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Aux-loss normalization in MoE models is unrelated to the T5 apex RMSNorm memory leak." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3OmniMoe video input ValueError is different from a flash-attention generation bug in Qwen3.5." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Loading Phi-4 multimodal fails for model reasons; MIN_PEFT_VERSION being unreleased is a dependency/versioning issue." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video-input regression across Qwen multimodal models is not the same as num_labels propagation in Qwen3.5." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "A SigLIP2 discrepancy is unrelated to gradient explosion under HfDeepSpeedConfig + ZeRO-3." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_id in Qwen3-VL text config is not the same as AutoModelForCausalLM.from_config failing to unwrap text_config." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "Smollm3 RoPE-layer counting is unrelated to the qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Defaulting mm_token_type_ids to zeros is a training-input bug, while the other is an inference OOM." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "A model load failure for sleng-bert is not the same as model_info() being called offline in _patch_mistral_regex." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Accelerate+deepspeed weight conversion and generic Qwen3VL MOE loading breakage are related in theme but not the same concrete bug." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Training/eval dtype mismatch is not the same as abnormal gradient growth under ZeRO-3." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Missing Qwen2_5_VL import and Float8 storage lookup failure are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage and lm_head.weight serialization inconsistency are different problems." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 multi-GPU inference OOM and a Gemma4 PLE device mismatch are distinct failures." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Float8 storage resolution and a Python 3.13 flash_attn import_utils KeyError are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "MoE auxiliary-loss normalization is not the same as a broad tokenization change across versions." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "Doc-example mistakes do not match the processor.tokenizer / image-passing regression." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Missing pad_token_idx after v5 update and unexpected _is_hf_initialized in init_empty_weights are different loading issues." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "A MacOS CLIP bus error is unrelated to Qwen2-VL multi-GPU training." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field loading failure in Beit is not the same as a CPU-offload device mismatch in bark-small." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "The serve multimodal '.to' crash and KV-cache continuation tensor-indexing bug affect different server paths." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "DiaConfig token persistence and MLukeTokenizer task errors are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 21, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29942", + "issue:30333", + "issue:33357", + "issue:34567", + "issue:38175", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43504", + "issue:43540", + "issue:43575", + "issue:43606", + "issue:43653", + "issue:43688", + "issue:43701", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44112", + "issue:44315", + "issue:44464", + "issue:44466", + "issue:44493", + "issue:44521", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44625", + "issue:44792", + "issue:44849", + "issue:44964", + "issue:45072", + "issue:45084", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45405", + "issue:45446", + "issue:45520", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43504|issue:43653", + "issue:43575|issue:45405", + "issue:44625|issue:45759", + "issue:43606|issue:44112", + "issue:44792|issue:45405", + "issue:43994|issue:44493", + "issue:44521|issue:45290", + "issue:44464|issue:45584", + "issue:29942|issue:30333", + "issue:43844|issue:44964", + "issue:28218|issue:34567", + "issue:45084|issue:45520", + "issue:44554|issue:45446", + "issue:44568|issue:45701", + "issue:43688|issue:43873", + "issue:15354|issue:38175", + "issue:43232|issue:44849", + "issue:43540|issue:45200", + "issue:45200|issue:45823", + "issue:45072|issue:45198", + "issue:44315|issue:44849", + "issue:43278|issue:43701", + "issue:28218|issue:33357", + "issue:44554|issue:45356", + "issue:45200|issue:45325", + "issue:44466|issue:45127", + "issue:43295|issue:44610" + ], + "prepared_review_unit_hash": "cde9e27e67ee89ac99f90bcdff79fd6451109859eb732514d96e2fb19f3f23e6", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35869, + "estimated_input_tokens": 8968, + "estimated_eval_tokens": 18192 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the items span unrelated tokenizer, multimodal, training, runtime, and CI failures. The soft pairs share only superficial vocabulary or a broad subsystem, not the same concrete bug or fix path, so none should be merged as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue stands out because the cluster is not a duplicate set; it mixes many unrelated bugs across different models and code paths.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a good global representative for the cluster; any choice would overfit one narrow bug and misrepresent the rest of the unrelated items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Both involve token-related behavior, but one is a BEiT model load failure from a legacy field and the other is a BigBirdTokenizer special-token registration bug. Different components and fixes." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "One is an OOM during tensor-parallel loading of a Qwen model; the other is a version/dependency issue with PEFT. Not the same bug path." + }, + { + "left": "issue:44625", + "right": "issue:45759", + "accept": false, + "reason": "Both mention Qwen 3.5 configs, but one is num_labels propagation and the other is AutoModelForCausalLM config unwrapping. Related area, different concrete defects." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Both are CI/device mismatch problems, but they affect different models, tests, and execution paths. Not mergeable into one fix." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "A failed janus image-generation test and an unreleased PEFT version bump are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "Siglip2 nonsensical outputs and a position-id key regression are different failures with different likely causes." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both touch apply_chat_template, but one is zero assistant masks for multimodal inputs and the other is a crash on tool-call messages with no content. Distinct edge cases." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Chunked generation with compiled forward and Whisper empty-transcription generation are unrelated generation bugs." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "A Flash Attention 2 test failure and an MLflow reporting issue are different subsystems and problems." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient growth during training and a model loading regression are not the same code-path issue." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing after added tokens and TrainerState token counters are unrelated." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Compile errors for non-template nodes and a Python 3.13 flash_attn import KeyError are unrelated." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "An MPS attention correctness bug and an incorrect PyTorch version check in flex_attention are different defects." + }, + { + "left": "issue:44568", + "right": "issue:45701", + "accept": false, + "reason": "The first is a specific add_special_tokens/BOS-EOS regression in one tokenizer; the second is a broad version-dependent tokenization change. Not the same bug." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization and quantization offloading are separate training/runtime issues." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export failure and zero probabilities from siglip2-base are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs update after sync_gpus and a Qwen3.5 hidden-states bug are different code paths." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-input processing in Qwen3OmniMoe and Gemma4 mm_token_type_ids defaults are different multimodal bugs." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "One is missing default mm_token_type_ids for text-only tuning; the other is a device mismatch in Gemma4 PLE with device_map=auto. Different fixes." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "Bfloat16 dtype mismatches in inference and Wav2Vec2 save_pretrained/tokenization failures are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel not applied with model_init and Qwen3.5 output_hidden_states behavior do not share a concrete bug." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "Embedding dtype changing between train/eval and resume_from_checkpoint key mismatch are unrelated." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer spacing after added tokens and a MacOS bus error in CLIP model loading are different problems." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness and a Kimi tokenizer codec regression are unrelated." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Defaulting mm_token_type_ids and incorrect temporal position scaling in Qwen2.5-VL are different multimodal bugs." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Inconsistent lm_head serialization and LoRA merge collapse with extended vocab are not the same underlying defect." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor/tokenizer API regression and OmDet processor image-size mismatch are separate multimodal issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 22, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43425", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43572", + "issue:43575", + "issue:43653", + "issue:43701", + "issue:43819", + "issue:43824", + "issue:43825", + "issue:43827", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43901", + "issue:43957", + "issue:43975", + "issue:44112", + "issue:44206", + "issue:44360", + "issue:44442", + "issue:44464", + "issue:44514", + "issue:44521", + "issue:44561", + "issue:44610", + "issue:44792", + "issue:44857", + "issue:44898", + "issue:44936", + "issue:44987", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45245", + "issue:45412", + "issue:45563", + "issue:45584", + "issue:45593" + ], + "soft_pairs": [ + "issue:44898|issue:45412", + "issue:37428|issue:43957", + "issue:43572|issue:44987", + "issue:43493|issue:43701", + "issue:43334|issue:43525", + "issue:43572|issue:43957", + "issue:43873|issue:44464", + "issue:43824|issue:43975", + "issue:43295|issue:43450", + "issue:43844|issue:44936", + "issue:43295|issue:43873", + "issue:38175|issue:45412", + "issue:37428|issue:43824", + "issue:42915|issue:43824", + "issue:44514|issue:44521", + "issue:44442|issue:45198", + "issue:38175|issue:43493", + "issue:43278|issue:43856", + "issue:43653|issue:44112", + "issue:43827|issue:43901", + "issue:43450|issue:43493", + "issue:44792|issue:45563", + "issue:43450|issue:43575", + "issue:45127|issue:45245", + "issue:44360|issue:44561", + "issue:43819|issue:45083", + "issue:44206|issue:45584", + "issue:43819|issue:44112", + "issue:37428|issue:43425", + "issue:44610|issue:44857", + "issue:43262|issue:43450", + "issue:44857|issue:45593", + "issue:43278|issue:43825" + ], + "prepared_review_unit_hash": "02a8a0df7796ea73592d5b83f4d6f53eb2da1a38657892ca9913eb5657274687", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36920, + "estimated_input_tokens": 9230, + "estimated_eval_tokens": 18716 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft pair looks like a true duplicate; the set is a heterogeneous mix of unrelated bugs, regressions, and docs issues. There are no PRs to triage here.", + "confidence": 0.9, + "canonical_issue_reason": "No single canonical issue for the whole set: the items span unrelated failure modes across imports, processors, training, generation, and docs, and none of the soft pairs are clear duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must be singled out, issue 44521 is the strongest standalone report because it is open, active, and concrete; however, it is not representative of the other issues as a duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Different models and failure classes: Perceiver image resolution bug vs RT-DETR memory release issue." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Both mention loading/import problems, but one is a missing symbol import and the other is a meta-device model-loading regression affecting different code paths." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Both are v5-era model-loading complaints, but they concern different configs/models and likely distinct fixes." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 implementation discrepancy is unrelated to a resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Both are missing pad_token_id errors, but they affect different model families and are not the same concrete bug." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "A StableLm config attribute issue is not the same as a broad meta-device loading breakage." + }, + { + "left": "issue:43873", + "right": "issue:44464", + "accept": false, + "reason": "Quantization/offloading behavior and compiled-forward chunked generation are separate subsystems and symptoms." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "Importing Qwen2.5-VL vs DeepSeek-Coder detokenization are unrelated failures." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor.tokenizer regression and batched video-shape bug are different processor problems." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "ZeRO-3 gradient inflation during training is unrelated to evaluate-after-train failure." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Custom processor API regression and quantization offloading are different bugs." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero probabilities and RT-DETR memory cleanup are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Different missing symbols from different transformer modules; not the same import breakage." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "FP8 config failure for Qwen3-MoE is unrelated to a Qwen2.5-VL import error." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both involve apply_chat_template, but one crashes on batched padding=False input while the other yields all-zero assistant masks; distinct symptoms and likely distinct bugs." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "FastSpeech2Conformer tokenizer loading and Wav2Vec2 save/tokenization failures are different tokenizer issues." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "SigLIP2 probability output issue and SigLIP2 JAX-vs-HF discrepancy overlap in model family but not the same concrete bug." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype drift in eval and Qwen3 MoE memory usage are unrelated training issues." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug is unrelated to a GraniteSpeech CI device-override test failure." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs-related, but they cover different pipeline APIs and different deprecations." + }, + { + "left": "issue:43450", + "right": "issue:43493", + "accept": false, + "reason": "Batched video processor shape bug and SigLIP2 implementation discrepancy are different subsystems and failures." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to a stale paged-generate warning." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Video processor batching and Qwen2 large-model TP OOM are not the same bug." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA merge collapse with tied embeddings is unrelated to the 2^24 category limit error." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "A DSA indexer architecture discussion is unrelated to removal of is_torch_fx_available breaking trust_remote_code models." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent mismatch and a qwen3_omni_moe helper behavior issue are different code paths." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Unsupported feature-extractor arg and Whisper empty-transcription failure are distinct regressions." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "DAC forward mismatch and GraniteSpeech CI device override are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "A specific import error is not the same as broad Torch 2.10 incompatibility." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor output size mismatch and float16 AMP loss crash are different failures." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio apply_chat_template sample-rate defaulting and video batching shape bugs are unrelated." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "AMP/CUDA loss instability and missing auxiliary losses with denoising off are different training bugs." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Training/eval dtype drift and a pipeline docs error are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 23, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28218", + "issue:29942", + "issue:32090", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:43335", + "issue:43388", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44292", + "issue:44351", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44561", + "issue:44568", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45459", + "issue:45478", + "issue:45491", + "issue:45520", + "issue:45588", + "issue:45593", + "issue:45712", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:45290|issue:45381", + "issue:43606|issue:45083", + "issue:45200|issue:45588", + "issue:43335|issue:43550", + "issue:44448|issue:44743", + "issue:37428|issue:44351", + "issue:43611|issue:43931", + "issue:44462|issue:44561", + "issue:39692|issue:43526", + "issue:44206|issue:45823", + "issue:44561|issue:44779", + "issue:43388|issue:43526", + "issue:43335|issue:43653", + "issue:45310|issue:45478", + "issue:43819|issue:44493", + "issue:45588|issue:45859", + "issue:43550|issue:44112", + "issue:44855|issue:45083", + "issue:29942|issue:32090", + "issue:43335|issue:43504", + "issue:43335|issue:45083", + "issue:39692|issue:44493", + "issue:44292|issue:45520", + "issue:38175|issue:44493", + "issue:44448|issue:44779", + "issue:28218|issue:35141", + "issue:43335|issue:45072", + "issue:43720|issue:44112", + "issue:43335|issue:45593", + "issue:44977|issue:45229", + "issue:44448|issue:44977", + "issue:44568|issue:45491", + "issue:43606|issue:44857", + "issue:45459|issue:45712", + "issue:44857|issue:45072" + ], + "prepared_review_unit_hash": "625bf2766c2e49dab8f7effbe3f73dc7f2330bc47dc41734496cf25308e0ca35", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38457, + "estimated_input_tokens": 9615, + "estimated_eval_tokens": 19486 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly noisy and spans unrelated bugs across tokenizers, modeling, CI, and flash-attention. The only clear duplicate pair is the Qwen3.5 MoE from_pretrained regression (45310/45478).", + "confidence": 0.94, + "canonical_issue_reason": "issue:45310 is the earliest, clearest report of the same Qwen3.5 MoE from_pretrained failure also reported in 45478, so it is the best canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the strongest representative because it is the same concrete bug as 45478 and is written as a focused reproducible regression report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Different bugs: chat template/tool-call handling vs qwen2.5-vl video position IDs." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "Different subsystems and failures: CPU offload device mismatch vs qwen3_omni_moe length helper behavior." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Unrelated: Gemma text-only mm_token_type_ids defaulting vs flash-attention sink-less s_aux=None crash." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "Different concrete bugs: SwitchTransformers sparse-layer config vs Bamba SDPA/torch.compile failure." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output regression is unrelated to qwen modular recurrent-state reset." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different missing symbols in different modules." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Model-loading prefix handling and Qwen3-VL weight-shape mismatch are separate issues." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer repo-file selection is unrelated to removal of is_torch_fx_available for trust_remote_code." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 documentation example errors and BeitImageProcessorFast label reduction are not the same bug." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Different runtime failures: unsupported center arg in LasrFeatureExtractor vs Gemma4 PLE device mismatch." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Trust_remote_code FX helper removal is unrelated to Deepseek tokenizer output regression." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Metrics label truncation in gather_for_metrics is different from Beit fast processor reduce_labels behavior." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and BigBirdTokenizer special-token registration are unrelated." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Exact same Qwen3.5 MoE from_pretrained error on transformers>=5.4.0; 45478 is a duplicate of 45310." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC latent/forward mismatch is unrelated to unexpected key warnings for position IDs." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Both involve flash-attention-related code, but one is an s_aux=None crash and the other is CPU-offload incompatibility in a different model path." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba SDPA compile failure is unrelated to a GraniteSpeech stale CI test override." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 IndentationError in DebertaV2Model is unrelated to qwen3_omni_moe length computation." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and Trainer _gpu_broadcast_one TypeError are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation is unrelated to BEiT semantic-segmentation pretrained loading with a legacy field." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers config bug and qwen3_omni_moe feature-length helper bug are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 doc example failures are not the same as position-id key warnings across models." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime failure is unrelated to Python 3.13 flash_attn import_utils KeyError." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 is a different bug from unexpected position-id keys." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output regression and Deepseek tokenizer regression are different code paths." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer adding extra spaces after added tokens is unrelated to embedding reinitialization in post_init." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet packed-weight loading and GraniteSpeech CI stale-device-override are different issues." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation is unrelated to D-FINE auxiliary-loss behavior when denoising is off." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU OOM are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Pegasus v4/v5 regression is unrelated to Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer BOS/EOS behavior and Gemma3 NaN embeddings from sliding-window attention are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch and float16 AMP crash in LwDetrImageLoss are different bugs." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer protobuf error handling and leftover dummy class cleanup are unrelated." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "LwDetrImageLoss AMP crash and bfloat16 dtype mismatch are different failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet and stays conservative on the soft-edge rejections. The only accepted duplicate pair, issue:45310 / issue:45478, is well supported by identical titles and the earlier date for 45310. The summary accurately reflects that the rest of the cluster is mostly unrelated noise." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 24, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:25251", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:37428", + "issue:40444", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43381", + "issue:43412", + "issue:43421", + "issue:43526", + "issue:43550", + "issue:43653", + "issue:43701", + "issue:43873", + "issue:43927", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44493", + "issue:44743", + "issue:44857", + "issue:44977", + "issue:45083", + "issue:45198", + "issue:45245", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45698", + "issue:45803", + "issue:45823" + ], + "soft_pairs": [ + "issue:29127|issue:32090", + "issue:44977|issue:45563", + "issue:43927|issue:45698", + "issue:45198|issue:45803", + "issue:34689|issue:35141", + "issue:45372|issue:45588", + "issue:40444|issue:43526", + "issue:43701|issue:45083", + "issue:43550|issue:45083", + "issue:43412|issue:45588", + "issue:45245|issue:45563", + "issue:43873|issue:44493", + "issue:29942|issue:35141", + "issue:36010|issue:37428", + "issue:43066|issue:44462", + "issue:45372|issue:45459", + "issue:44857|issue:45588", + "issue:44448|issue:44466", + "issue:43065|issue:45412", + "issue:45588|issue:45823", + "issue:43278|issue:43381", + "issue:43653|issue:44743", + "issue:25251|issue:32090", + "issue:44451|issue:45520", + "issue:43976|issue:45440", + "issue:44186|issue:45198", + "issue:42915|issue:42994", + "issue:43994|issue:45412", + "issue:43421|issue:45491" + ], + "prepared_review_unit_hash": "b1b683106585e034d9b7fe98b643d7afeb8f00155c315c503ab6f7f458dbbd9b", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36376, + "estimated_input_tokens": 9094, + "estimated_eval_tokens": 18444 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the soft-similarity pairs mostly link unrelated bugs across different models, tokenizer paths, export flows, and trainer/runtime behaviors. I do not see a single underlying duplicate issue or a safe canonical representative.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "Different failures: LayoutLMv3 error handling for insufficient box info vs Trainer GPU broadcast rejecting NoneType." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug is unrelated to a stale warning in paged generate()." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load behavior, but one is DiaConfig custom token IDs and the other is loading the wrong custom module." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure is unrelated to FuyuBatchFeature swallowing exceptions." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model loading breakage for Llama 3.2 vision is unrelated to embedding reinitialization after resizing token embeddings." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Different import/runtime bugs: missing ReasoningEffort vs flash_attention.py crashing on s_aux=None." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Qwen2.5-VL iterable dataset with multiple images is unrelated to BeitImageProcessorFast returning only one label." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile + SDPA bug in Bamba-9B-v2 is a different code path than qwen3_omni_moe length computation." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Gemma3 executorch export issues are unrelated to flash_attention integration crashing on sink-less models." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-cardinality runtime error is unrelated to a stale num_return_sequences warning." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior differs from position-id unexpected-key loading issues." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to token embedding resizing and post_init reinitialization." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "Different missing-import regressions: GenerationMixin vs _flash_supports_window_size." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer decoder type mismatch in v5 is not the same as AutoTokenizer ignoring tokenizer.json." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Different tokenizer/import problems: missing ReasoningEffort vs overly broad protobuf exception handling." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "AMP/CUDA loss crash is unrelated to flash_attention.py s_aux=None AttributeError." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Pegasus output differences across versions are not the same as inconsistent lm_head.weight serialization." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to RT-DETR memory not being released." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Flash-attention crash with s_aux=None is unrelated to Gemma4 PLE device mismatch during forward." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype drift in eval is a different issue from gradient checkpointing being unusable in eval mode." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug is unrelated to qwen3_5 recurrent state reset behavior." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nested-list output is unrelated to Trainer _gpu_broadcast_one rejecting NoneType." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model load failure for ScandiBERT is unrelated to Python 3.13 flash_attn import KeyError." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility for 5.1.0 is unrelated to DeepseekV3MoE divergence from remote implementation." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes on NER/padding are unrelated to Wav2Vec2 save_pretrained/tokenization failures." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure is a different problem from quantized model saving." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 nonsensical outputs with AutoModel/pipeline are unrelated to RT-DETR memory release." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "TokenizerBackend post-processor updates are unrelated to Gemma3 NaN embeddings from sliding-window attention." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 25, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:43065", + "issue:43278", + "issue:43329", + "issue:43334", + "issue:43381", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43653", + "issue:43701", + "issue:43723", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43873", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44279", + "issue:44361", + "issue:44442", + "issue:44479", + "issue:44554", + "issue:44610", + "issue:44734", + "issue:44871", + "issue:44977", + "issue:45103", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45593", + "issue:45834", + "issue:45859" + ], + "soft_pairs": [ + "issue:44361|issue:45198", + "issue:44871|issue:44977", + "issue:44206|issue:44479", + "issue:44265|issue:45198", + "issue:29942|issue:30064", + "issue:44734|issue:45406", + "issue:43065|issue:43994", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:44610|issue:45412", + "issue:45103|issue:45372", + "issue:43756|issue:45440", + "issue:43723|issue:44554", + "issue:43873|issue:45229", + "issue:45372|issue:45406", + "issue:43761|issue:45859", + "issue:43278|issue:43575", + "issue:43526|issue:45834", + "issue:43381|issue:43701", + "issue:43653|issue:44442", + "issue:45440|issue:45593", + "issue:41720|issue:45229", + "issue:43278|issue:43329", + "issue:29942|issue:36010", + "issue:43334|issue:43531", + "issue:32090|issue:33357", + "issue:44977|issue:45245", + "issue:43526|issue:44186", + "issue:43824|issue:44279" + ], + "prepared_review_unit_hash": "dd9c4c163e8b46ce634c3c1e9a6eed0bbca3b2c77000b7671a3a36ab192bb3e0", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36452, + "estimated_input_tokens": 9113, + "estimated_eval_tokens": 18482 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is broad and mostly heterogeneous: the soft links are driven by shared Transformers subsystems and regression language, not the same underlying bug. All soft pairs should be rejected as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 43723 is the broadest and most generic loading-regression report in the set, so it is the weakest but most usable anchor if one issue must represent the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43723 is the best umbrella-style issue because it describes a general AutoTokenizer loading failure, but it still does not cover the many model- and processor-specific reports here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "Both involve tokenizer/task failures, but they are different concrete bugs on different models and code paths." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Both mention generation/eos behavior, but one is a Gemma-3 config mismatch and the other is a Qwen3.5 flash-attention generation issue." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "These are separate regression reports in different components: feature extractor argument handling vs video-input regression for multiple Qwen VL models." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failures with torch_compilable_check are unrelated to Wav2Vec2 save_pretrained/tokenization failures." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures and void segmentation map processing are unrelated bugs." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "Both crash in serving, but one is KV-cache continuation indexing and the other is Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Both are model-specific vision issues, but one is a dummy Conv2d in Sam3PixelDecoder and the other is SigLIP2 inference nonsense outputs." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "Both mention CLIP/SigLIP-style models, but one is a MacOS bus error and the other is a documentation example/model-processor mismatch plus quantization failure." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error messaging and TrainerState token counting are unrelated issues." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor image-size mismatch and RT-DETR memory release are different problems in different subsystems." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation handling and Gemma4 processor loading/import failure are not the same bug." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Smollm3 RoPE-layer mismatch and DeepseekV3MoE divergence are unrelated model-implementation issues." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading regression and MPS attention correctness are separate code paths and behaviors." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantization/offloading behavior and Gemma4 multi-GPU OOM are different resource-management problems." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Gemma4 processor import dependency failure and transformers serve processor attribute failure are related to Gemma4 but not the same concrete bug." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43575", + "accept": false, + "reason": "Embedding dtype drift and tensor-parallel OOM are distinct issues with no shared failing code path." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and Kosmos2.5 long-OCR indexing are different processor bugs." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode and resume_from_checkpoint key mismatch are unrelated trainer behaviors." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and AutoTokenizer loading of FastSpeech2ConformerTokenizer are different tokenizer bugs." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepseekV3MoE divergence and D-FINE auxiliary-loss handling are unrelated model/training issues." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3 auto device mapping cudaErrorAssert and Gemma4 multi-GPU OOM are both GPU problems but not the same failure." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype mismatch and multimodal token counting with undefined video helpers are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failures and GenerationMixin import failure are different regressions." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL pad_token_id loading failure and Qwen3-MoE sliding_window issue are distinct model config bugs." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer NoneType broadcast and MacOS bus error on CLIP are unrelated runtime failures." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation and category-count runtime error are different problems." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and LayoutLMv2Tokenizer NER/padding crashes are separate tokenizer/processor bugs." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Qwen2_5_VL import failure and a generic dependency issue with transformers are not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 26, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:42907", + "issue:42915", + "issue:43262", + "issue:43316", + "issue:43381", + "issue:43441", + "issue:43525", + "issue:43526", + "issue:43575", + "issue:43611", + "issue:43646", + "issue:43701", + "issue:43761", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44079", + "issue:44188", + "issue:44206", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44479", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44898", + "issue:44964", + "issue:44977", + "issue:45072", + "issue:45216", + "issue:45290", + "issue:45440", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45698", + "issue:45803" + ], + "soft_pairs": [ + "issue:43526|issue:44857", + "issue:43441|issue:45588", + "issue:43262|issue:44206", + "issue:44464|issue:45491", + "issue:42915|issue:43931", + "issue:44442|issue:45072", + "issue:44743|issue:44811", + "issue:43575|issue:43701", + "issue:43646|issue:44077", + "issue:29127|issue:35141", + "issue:44442|issue:45803", + "issue:43575|issue:44387", + "issue:44977|issue:45584", + "issue:33357|issue:38175", + "issue:43316|issue:43525", + "issue:44964|issue:45440", + "issue:44479|issue:45290", + "issue:43761|issue:44079", + "issue:28218|issue:29127", + "issue:42907|issue:45698", + "issue:43931|issue:45216", + "issue:28218|issue:32090", + "issue:39692|issue:45491", + "issue:33290|issue:34567", + "issue:34689|issue:43611", + "issue:44442|issue:44898", + "issue:43761|issue:44188", + "issue:43381|issue:43873" + ], + "prepared_review_unit_hash": "0ffb20091d0301aa5de1bfcd65ccc8d0ee5a6cbfff955ebf951c286e113250f6", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36130, + "estimated_input_tokens": 9033, + "estimated_eval_tokens": 18322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All soft pairs should be rejected; they are mostly same-subsystem, same-model, or same-surface-symptom matches without enough evidence for a shared underlying bug. In particular, 43761 and 44079 only share a broad ModelOutput/hidden-state theme, and the CLIPVisionModel regression is not shown to be the same code-path bug as the generic key-assignment issue.", + "confidence": 0.87, + "canonical_issue_reason": "No duplicate canonicalization is well-supported here. issue:44079 is the broader ModelOutput report, but the packet does not establish that issue:43761 is the same underlying bug rather than a separate CLIPVisionModel regression.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44079 is the best standalone representative of the generic ModelOutput key-assignment problem, but only as the broader report, not as a proven duplicate of issue:43761.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "Different components and failure modes: BeitImageProcessorFast label reduction vs LwDetr AMP/CUDA crash." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Both mention flash attention, but they describe different concrete bugs and code paths." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio/processor regressions, but sampling-rate defaulting and unsupported center-arg crashes are different issues." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Different symptoms and paths: compiled chunked generation inconsistency vs NaN embeddings from sliding-window attention." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "Distinct loading failures on different model families and different root causes." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure and dtype mismatch are unrelated problems." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Different modules and behavior: recurrent-state reset vs Whisper batch_decode special-token handling." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "OOM during tensor-parallel loading is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "One is a generic custom-init regression; the other is a specific optional post_init policy issue, not the same bug." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "Different LayoutLMv3 error-reporting issue vs embedding reinitialization bug." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer load failure is unrelated to the bare-except error handling bug in Fuyu batch conversion." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both are OOM reports, but the causes differ: tensor-parallel loading vs int4 quantization memory regression." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Different generation bugs in different models and code paths." + }, + { + "left": "issue:33357", + "right": "issue:38175", + "accept": false, + "reason": "Different models and symptoms: MacOS bus error vs zero-probability outputs." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config/API mismatches, but they involve different attributes and different model classes." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Different multimodal loading regressions with no shared concrete code-path evidence." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression and chat-template/tool-call crash are unrelated failures." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "The CLIPVisionModel hidden_states=None symptom is not explicitly shown to come from the generic ModelOutput key-assignment bug; the match is only thematic." + }, + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Tokenizer spacing regression and LayoutLMv3 error-message clarity issue are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Both touch save/load flows, but dequantized-save failure and wrong custom-module reload are different bugs." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Different Qwen loading regressions with different failure modes." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer spacing bug and Trainer GPU broadcast NoneType error are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:45491", + "accept": false, + "reason": "Documentation/example errors are not the same as a runtime NaN regression." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "AdaFactor/deepspeed OOM and TrainerState token counter not updating are unrelated." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "One is a specific model-loading break, the other is a broader base_model_prefix regression." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer loading failure and Perceiver interpolation failure are unrelated." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "ModelOutput key handling and attention-kernel branching under torch.compile are different code paths." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode and offloading OOM are unrelated." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary overstates the evidence for the only accepted soft pair. In the packet, `issue:43761` and `issue:44079` are only linked by soft similarity, and the deterministic verdict is false; there is no explicit evidence that the CLIPVisionModel symptom is the same bug as the generic `ModelOutput` key-assignment issue. The rest of the pairwise rejections are conservative, but the canonical/best-issue conclusion should not be presented as grounded enough to accept." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 27, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:25251", + "issue:28282", + "issue:29127", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34689", + "issue:36010", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:43232", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43475", + "issue:43493", + "issue:43540", + "issue:43550", + "issue:43643", + "issue:43720", + "issue:43742", + "issue:43825", + "issue:43827", + "issue:43856", + "issue:43873", + "issue:44077", + "issue:44162", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44568", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45137", + "issue:45372", + "issue:45479", + "issue:45656", + "issue:45759" + ], + "soft_pairs": [ + "issue:43550|issue:44743", + "issue:43493|issue:43827", + "issue:44568|issue:45479", + "issue:43316|issue:45759", + "issue:41628|issue:45372", + "issue:43643|issue:44913", + "issue:43720|issue:44442", + "issue:32090|issue:33290", + "issue:44190|issue:44496", + "issue:43873|issue:44871", + "issue:34689|issue:36010", + "issue:43381|issue:43856", + "issue:44077|issue:44479", + "issue:44855|issue:45137", + "issue:33290|issue:45656", + "issue:43316|issue:44877", + "issue:43540|issue:44514", + "issue:29127|issue:33357", + "issue:42175|issue:43316", + "issue:43381|issue:43742", + "issue:33290|issue:34689", + "issue:44162|issue:44792", + "issue:43404|issue:43441", + "issue:25251|issue:28282", + "issue:43232|issue:43388", + "issue:41950|issue:43475", + "issue:43295|issue:43825" + ], + "prepared_review_unit_hash": "e0e487bd4387ded4da5468617ee5c1c669370ed45f13073464d094462b9acf35", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36090, + "estimated_input_tokens": 9023, + "estimated_eval_tokens": 18302 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These soft pairs are mostly topical neighbors, not true duplicates. They span distinct regressions across model loading, config handling, pipelines, deepspeed, tokenizers, and multimodal processing, so the safe triage outcome is to reject all suggested merges.", + "confidence": 0.91, + "canonical_issue_reason": "If one issue must serve as a representative, issue 43825 is the clearest user-facing regression with a specific, narrow failure mode; however, there is no single canonical issue for the whole set because the candidates are not one duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43825 is the best overall representative among this set: it is concrete, reproducible, and describes a clear behavior regression rather than a broad symptom or vague compatibility complaint.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "Different bugs: torch.compile/SDPA failure in Bamba vs recurrent state reset in modular_qwen3_5 cache handling." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "One is a SigLIP2 implementation parity discrepancy; the other is stale docs referencing removed pipelines." + }, + { + "left": "issue:44568", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer special-token behavior is unrelated to the single-label-classification zero-loss bug." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config/model loading, but the concrete problems differ: Gemma3TextConfig API mismatch vs not unwrapping text_config for Qwen multimodal configs." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Both are import errors, but they arise from different missing symbols and different loading paths/models." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "Generic config-roundtrip issue vs a specific rotary_pct value being lost on reload; not the same underlying bug." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "Accelerate loading of packed BitNet weights is unrelated to AutoTokenizer failing on FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "NoneType GPU broadcast error and Adafactor OOM in deepspeed are distinct training failures with different causes." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in an example script is unrelated to an unrecognized model/config loading error." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior and Gemma-3 eos_token_id inconsistency are different code paths and symptoms." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Model-loading regression for Llama 3.2 vision is not the same as the GenerationMixin import-path breakage." + }, + { + "left": "issue:43381", + "right": "issue:43856", + "accept": false, + "reason": "Gradient checkpointing in eval mode is a functional error; Qwen3 MoE memory inefficiency is a performance issue." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "PatchTSTMixer post_init validation is unrelated to the Qwen video-input regression." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 IndentationError in a scripted decorator block is unrelated to DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "Both mention deepspeed/optimizer behavior, but one is OOM with Adafactor and the other is a double optimizer-step bug." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy is not the same as strict config validation blocking granite_speech loading." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Video-input processing failure in Qwen3OmniMoe is different from batched apply_chat_template crashing with padding=False." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 box-content validation and a MacOS CLIP bus error are unrelated failures." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Missing tensorflow backend after pip install '.[torch]' is unrelated to a Gemma3TextConfig API discrepancy." + }, + { + "left": "issue:43381", + "right": "issue:43742", + "accept": false, + "reason": "Gradient-checkpointing/eval-mode behavior does not match the MobileLLM key-error during model loading." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Deepspeed Adafactor OOM and Llama 3.2 vision load regression are different failure modes." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 being broken and a janus image-generation test failure are different model-specific issues." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Weight tying in Mistral3ForConditionalGeneration is a different bug from FlashAttention failures in Ministral-3." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline top_k nested-list output and AutoModel missing PyTorch are unrelated issues." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs ordering after sync_gpus is not the same as gather_for_metrics dropping tuple label elements." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Video-classification pipeline using image processors and SAM3 vision encoder missing an attribute are different bugs." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Custom processor.tokenizer regression is different from pipeline() still suggesting translation tasks in v5." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 28, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:33290", + "issue:35141", + "issue:36331", + "issue:41720", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43452", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43742", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44190", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44737", + "issue:44743", + "issue:44792", + "issue:44871", + "issue:44913", + "issue:44936", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45584", + "issue:45600", + "issue:45698", + "issue:45803" + ], + "soft_pairs": [ + "issue:45127|issue:45200", + "issue:44871|issue:45584", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43295|issue:44871", + "issue:43065|issue:44617", + "issue:43761|issue:44479", + "issue:43673|issue:44743", + "issue:33290|issue:35141", + "issue:43452|issue:44496", + "issue:33290|issue:36331", + "issue:44936|issue:45698", + "issue:43646|issue:44913", + "issue:43575|issue:43742", + "issue:42617|issue:43575", + "issue:43761|issue:44242", + "issue:43575|issue:43873", + "issue:44077|issue:44534", + "issue:43931|issue:44060", + "issue:44464|issue:44871", + "issue:44479|issue:44734", + "issue:44617|issue:45584", + "issue:43906|issue:45290", + "issue:44792|issue:44977", + "issue:43065|issue:44610", + "issue:43827|issue:43994", + "issue:44534|issue:44913", + "issue:44190|issue:44964", + "issue:41720|issue:45245", + "issue:44792|issue:45600", + "issue:44737|issue:45803" + ], + "prepared_review_unit_hash": "dbb379f341b5b7abd1a2870794acc0b5f8d9ec9a3298b3910869cce91ce63f30", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36942, + "estimated_input_tokens": 9236, + "estimated_eval_tokens": 18728 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a duplicate family; it mixes many unrelated issues spanning model loading, generation, training, serialization, docs, and model-specific regressions. No single canonical issue/PR stands out.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "Both mention embeddings/tied weights, but one is LoRA merge collapse after vocab extension and the other is Gemma 4 token_type_ids defaulting; different bugs and code paths." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Gemma eos_token_id config mismatch vs Whisper empty-transcription failure after align_special_tokens; unrelated symptoms and components." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile+SDPA generation failure vs resume_from_checkpoint key mismatch; different subsystems and root causes." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch vs checkpoint key mismatch; no shared underlying bug." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Processor/tokenizer API regression vs eos_token_id configuration inconsistency; different regression classes." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs Sam3Video CUDA OOM; one is code correctness, the other capacity/memory." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVision hidden_states regression vs Qwen video input regression; different models and failure modes." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both involve cache/state handling, but one is missing GenerationMixin cache in chunked_prefill and the other resets recurrent states in modular_qwen3_5.py; not the same bug." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "AdaFactor/DeepSpeed OOM vs embeddings reinitialized after resize; unrelated training and model-init issues." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "GGUF loading breakage vs unrecognized model/config.json issue; both loading-related but distinct root causes." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "OOM in DeepSpeed optimizer vs custom trainer compute_loss signature mismatch; completely different problems." + }, + { + "left": "issue:44936", + "right": "issue:45698", + "accept": false, + "reason": "trainer.evaluate() after train failure vs wrong custom module loaded after save_pretrained; different lifecycle stages and bugs." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Custom model initialization regression vs GPTNeoX rotary_pct not persisting on reload; both config/init-related, but not the same issue." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Qwen2-57B-A14B-Instruct tensor-parallel OOM vs MobileLLM load key error; unrelated model-loading failures." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel.py runtime failure vs Qwen2 TP OOM; no common code path beyond generic runtime failures." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Hidden_states regression in CLIPVision vs MoE load-balancing loss omission; unrelated model behaviors." + }, + { + "left": "issue:43575", + "right": "issue:43873", + "accept": false, + "reason": "Both touch memory/offload concerns, but one is TP loading OOM and the other is quantization offloading not behaving as expected; different mechanisms." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Optional post_init allowance vs non-persistent buffers filled with junk; both v5-related, but different internals." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch vs incorrect tied-weights warning in Qwen3-Next; different models and bugs." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency vs Gemma eos_token_id config mismatch; unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Video-input regression for Qwen VL models vs serve KV-cache continuation tensor indexing bug; different surfaces and root causes." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Sam3Video OOM vs Whisper empty transcription after token alignment; unrelated model families and failure modes." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "Isolated reproduction of an external issue vs apply_chat_template crash with tool-call messages; no evidence they are the same bug." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Janus image-generation test failure vs Qwen3.5 flash-attention generation issue; different models and code paths." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Sam3PixelDecoder dummy Conv2d vs OmDet-Turbo processor output-size mismatch; unrelated bugs." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() vs SigLIP2 producing nonsensical results with AutoModel/pipeline; one is documentation debt, the other is model behavior." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffers junk vs rotary_pct resetting on reload; both serialization-ish, but not the same underlying defect." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading in no_trainer script vs Phi-4 multimodal model loading failure; unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert vs category-count limit error; completely different issues." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Janus generation test failure vs auto_mappings referencing removed configs and breaking CI; unrelated." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "XLNet CPU device bug in relative positional encoding vs bare except swallowing KeyboardInterrupt in FuyuBatchFeature; different code paths and bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 29, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:41628", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43335", + "issue:43404", + "issue:43479", + "issue:43540", + "issue:43550", + "issue:43644", + "issue:43650", + "issue:43976", + "issue:44077", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44464", + "issue:44466", + "issue:44496", + "issue:44521", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44855", + "issue:44877", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:45127", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45357", + "issue:45362", + "issue:45375", + "issue:45381", + "issue:45446", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45632", + "issue:45803" + ], + "soft_pairs": [ + "issue:44855|issue:45588", + "issue:44521|issue:45381", + "issue:45127|issue:45357", + "issue:43335|issue:44855", + "issue:44938|issue:45542", + "issue:43976|issue:44855", + "issue:44496|issue:45803", + "issue:43550|issue:44190", + "issue:44077|issue:44877", + "issue:43644|issue:44913", + "issue:43540|issue:44734", + "issue:45276|issue:45584", + "issue:44112|issue:45600", + "issue:43650|issue:44220", + "issue:43335|issue:44190", + "issue:43116|issue:44190", + "issue:45245|issue:45584", + "issue:43295|issue:45276", + "issue:43479|issue:45375", + "issue:36246|issue:41628", + "issue:44464|issue:45563", + "issue:44933|issue:45362", + "issue:44186|issue:44734", + "issue:43404|issue:45216", + "issue:44734|issue:45632", + "issue:44683|issue:45446", + "issue:38175|issue:43065", + "issue:44561|issue:45632", + "issue:44466|issue:44913" + ], + "prepared_review_unit_hash": "b4eee857f1d04f5d74f07d125298c929bdfffe5fb62c5058cef57dac547049e0", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35959, + "estimated_input_tokens": 8990, + "estimated_eval_tokens": 18236 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is largely heterogeneous and does not contain clear duplicate pairs; most candidates only share a broad subsystem or theme rather than the same underlying bug. The strongest standalone issue in the cluster is the open multimodal chat-template bug.", + "confidence": 0.88, + "canonical_issue_reason": "issue:44521 is the clearest high-signal report: open, well-discussed, and specific about a reproducible multimodal `apply_chat_template` failure with broad user impact.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the best representative issue because it is active, clearly described, and has the most evidence of ongoing relevance compared with the more isolated, model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Both are runtime failures, but one is a Python 3.13 import/parsing issue in DebertaV2 while the other is an `s_aux=None` flash-attention crash; different code paths and fixes." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both involve multimodal processing, but one is about assistant mask generation in chat templating and the other about video `vision_position_ids` in Qwen2.5-VL; not the same bug." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "These are different Qwen save/merge regressions: one concerns LoRA merge with tied embeddings, the other incorrect visual encoder keys in `save_pretrained`." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "Unrelated issues: SwitchTransformers sparse-layer config creation versus a DebertaV2 Python 3.13 import error." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Both are import/load failures, but the causes differ: Python 3.14 compatibility versus missing TensorFlow backend handling when only tensorboard is installed." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "One is a broad Python-version incompatibility claim for Transformers 5.1.0; the other is a model import failure on Python 3.13. Different underlying problems." + }, + { + "left": "issue:44496", + "right": "issue:45803", + "accept": false, + "reason": "No shared bug: unrecognized model config loading versus a bare `except` swallowing interrupts in Fuyu tensor conversion." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "Different surfaces and fixes: SDPA/torch.compile behavior in Bamba versus a local dataset loading problem in an example script." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "Both mention config behavior, but one is about `post_init` allowance in patchtsmixer and the other about strict loading for granite_speech configs; not the same defect." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Distinct issues: junk-filled non-persistent buffers in v5 versus `rotary_pct` not persisting on GPTNeoX config reload." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Different bugs: Qwen3OmniMoe video input validation versus KV-cache continuation tensor indexing in the serve API." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "One is embedding resizing not propagating in gemma4; the other is Whisper generation failing on empty transcription after token alignment." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "A flaky GraniteSpeech CI test and a broken auto-mapping reference to removed Sam3LiteText configs are separate CI/config issues." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "`ADD THE DATA` is a low-information issue and `_torch_extract_fbank_features()` is a specific audio-processing bug; no evidence they are the same." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "Unrelated: SwitchTransformers sparse-layer config bug versus image-classification script dataset loading failure." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Different example-script problems in different tasks: multi-label classification output handling versus local dataset loading for image classification." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "No overlap in concrete failure mode: category-count limit error versus Whisper empty-transcription generation failure." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Different regression classes: processor/tokenizer API breakage versus embedding resize not updating tied outputs." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Both are multimodal config issues, but they concern different models and fields: default vision/audio config initialization versus a missing `deepstack_visual_indexes` field." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they involve different symbols and modules (`Qwen2_5_VLImageProcessor` vs `AutoImageProcessor`); no shared underlying bug is evident." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Generation-related, but one is inconsistent outputs under compiled forward and the other is a stale warning in paged generate; different issues and fixes." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "A missing import from `image_utils` is unrelated to Qwen3.5 chat crashes." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Tokenizer padding/NER crashes and serve KV-cache indexing are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Both touch model weights, but one is untied `lm_head` in Mistral3 and the other is incorrect `save_pretrained` checkpoints for Qwen3.5; not the same code path." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Both are in flex_attention, but one is a compiled runtime failure on torch>=2.9 and the other is a wrong version check for AuxRequest import; separate bugs." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Unrelated model-specific issues: zero probabilities in SigLIP2 versus a dummy Conv2d in Sam3PixelDecoder." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Different trust_remote_code problems: removed helper function breaking remote models versus cache-path collisions for local models." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Serialization of tied `lm_head.weight` depends on device versus GPTNeoX config reload losing `rotary_pct`; not the same defect." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 30, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36246", + "issue:38617", + "issue:41950", + "issue:42175", + "issue:42907", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43643", + "issue:43673", + "issue:43688", + "issue:43827", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44279", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44496", + "issue:44964", + "issue:45003", + "issue:45020", + "issue:45042", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45406", + "issue:45563", + "issue:45584", + "issue:45593", + "issue:45600", + "issue:45632", + "issue:45759" + ], + "soft_pairs": [ + "issue:44246|issue:45003", + "issue:36246|issue:38617", + "issue:43643|issue:44496", + "issue:45406|issue:45632", + "issue:45563|issue:45584", + "issue:41950|issue:44016", + "issue:43388|issue:43688", + "issue:44964|issue:45600", + "issue:42907|issue:43441", + "issue:44112|issue:44964", + "issue:43295|issue:45335", + "issue:43854|issue:44964", + "issue:44496|issue:45042", + "issue:43673|issue:44336", + "issue:44016|issue:44220", + "issue:43299|issue:45216", + "issue:43531|issue:45600", + "issue:43526|issue:43901", + "issue:42175|issue:44279", + "issue:45335|issue:45584", + "issue:44075|issue:44368", + "issue:43381|issue:45593", + "issue:43299|issue:45357", + "issue:43901|issue:44496", + "issue:44496|issue:45759", + "issue:44351|issue:45278", + "issue:44242|issue:45200", + "issue:44016|issue:44062", + "issue:43388|issue:43827", + "issue:41950|issue:45020", + "issue:43976|issue:45405" + ], + "prepared_review_unit_hash": "32fcb3b48dcc839df931b16c2162da34fd1690627e0c53d26e65bd85aea8f989", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37050, + "estimated_input_tokens": 9263, + "estimated_eval_tokens": 18782 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No strong duplicate cluster emerged. The items span distinct regressions across imports, model loading/saving, pipelines, generation, training, and docs. I rejected all soft pairs because they do not appear to be the same underlying bug or change.", + "confidence": 0.82, + "canonical_issue_reason": "issue:45278 is the broadest umbrella report in the set: it describes multiple import errors after upgrading to 5.5.0, which is the closest match to the repeated import/load-regression theme across several items.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best representative issue because it is open, broad, and phrased as a general post-upgrade failure rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "One is an intermittent import-performance complaint; the other is a specific sys.modules safety issue in modeling_utils. Different bugs and different symptoms." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Both are ImportErrors, but for different missing symbols in different modules. No evidence they stem from the same regression." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "One is about trust_remote_code returning incomplete config fields; the other is an unrecognized model because config.json lacks model_type. Related area, but not the same bug." + }, + { + "left": "issue:45406", + "right": "issue:45632", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer in serve is unrelated to cache-path collisions for local trust_remote_code models." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Different generation bugs: stale num_return_sequences warning vs Whisper empty-transcription failure after token alignment." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Video-classification pipeline lookup bug and a notebook syntax error are unrelated." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Gather-for-metrics label truncation and auxiliary-loss normalization are separate training/eval issues." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Both touch model loading/mappings, but one is a Phi-4 multimodal load failure and the other is stale auto_mappings references. Different code paths." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Same model family, but one concerns saving dequantized Ministral/Devstral models and the other FlashAttention load/runtime failure. Not the same bug." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "A CI test/device override failure in GraniteSpeech is unrelated to loading Phi-4 multimodal models." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Processor/tokenizer regression in custom multimodal code is unrelated to t5gemma embedding resize behavior." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Different model-specific load failures with no shared concrete bug." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Missing model_type in config is unrelated to PIL image processors requiring torchvision." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache missing and stray ANSI codes in loading_report are unrelated." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error and _torch_extract_fbank_features() bug are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Both involve Qwen 3.x multimodal regressions, but one is a load failure and the other is an incorrect save_pretrained checkpoint layout. Different bugs." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to stale auto_mappings references." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BEiT label reduction bug and text-classification docs mismatch are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Packaging/backend extra omission and a generic dependency issue are too vague and not the same concrete problem." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Different model/generation bugs with no shared code path." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Optimizer argument handling and a Qwen tie_word_embeddings warning are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing eval-mode restriction and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen multimodal regressions, but one is model loading and the other is incorrect visual-encoder key saving. Not the same underlying change." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to model config import/load failure." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Missing model_type for an unrecognized model is not the same bug as AutoModelForCausalLM failing to unwrap text_config for composite multimodal configs." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "A specific HybridCache import error may be one example of import breakage, but 45278 is only a broad umbrella report; there is not enough evidence they are the same concrete bug." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Missing load-balancing loss when router logits are off and Gemma 4 mm_token_type_ids defaults are different issues." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and AddedToken keyword collision are unrelated." + }, + { + "left": "issue:43388", + "right": "issue:43827", + "accept": false, + "reason": "Evaluation batching bug and outdated docs about pipeline() are unrelated." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification pipeline image-processor lookup and remote_code breakages are different problems." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python-version compatibility and an unreleased PEFT version bump are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 31, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42994", + "issue:43065", + "issue:43295", + "issue:43299", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43479", + "issue:43525", + "issue:43577", + "issue:43650", + "issue:43723", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44297", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44683", + "issue:44779", + "issue:44898", + "issue:44933", + "issue:44987", + "issue:45081", + "issue:45216", + "issue:45276", + "issue:45290", + "issue:45325", + "issue:45397", + "issue:45405", + "issue:45542", + "issue:45600", + "issue:45712", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:43824|issue:44933", + "issue:43577|issue:45216", + "issue:43479|issue:43525", + "issue:41950|issue:45823", + "issue:44683|issue:45542", + "issue:43299|issue:43854", + "issue:44279|issue:45405", + "issue:38175|issue:44617", + "issue:39692|issue:43901", + "issue:32090|issue:35141", + "issue:44297|issue:44462", + "issue:44462|issue:45081", + "issue:43295|issue:44779", + "issue:41950|issue:43650", + "issue:43976|issue:44279", + "issue:43976|issue:44987", + "issue:45600|issue:45712", + "issue:44462|issue:44779", + "issue:44521|issue:45325", + "issue:43441|issue:45834", + "issue:43450|issue:44279", + "issue:42994|issue:43317", + "issue:44261|issue:44263", + "issue:43065|issue:44898", + "issue:44466|issue:45276", + "issue:43650|issue:45290", + "issue:43441|issue:44683", + "issue:43723|issue:44162", + "issue:44623|issue:45397" + ], + "prepared_review_unit_hash": "eff1888d36629e23529edd02b67a235bc71c1ccb5ec16709b776c0bbcc6e44a6", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36324, + "estimated_input_tokens": 9081, + "estimated_eval_tokens": 18418 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated issues; the soft pairs are only superficially similar and do not look like the same underlying bug/change. I would not deduplicate any of the proposed pairs.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue stands out because this set does not form one coherent duplicate cluster; the proposed pairs span different models, subsystems, and failure modes.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue for dedupe triage here: the items are heterogeneous, and none of the soft pairs is a convincing duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but they concern different symbols and modules; no shared code path is evident." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "Different models and different bugs: BLIP2 dtype handling vs Qwen3.5 checkpoint serialization." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Both involve config objects, but one is multimodal default config initialization and the other is a missing pad_token_id attribute." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Different pipelines and failures: video-classification processor lookup vs Gemma4 device placement in forward." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Unrelated failures: torch 2.9 flex_attention compilation vs a TensorBoard/TensorFlow backend dependency issue." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Both are model loading problems, but they affect different model families and failure mechanisms." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "Too generic to merge: one is a vague dependency complaint, the other is a specific PEFT minimum-version bump issue." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "Different subsystems and symptoms: SigLIP2 zero probabilities vs Sam3Video CUDA out-of-memory." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs-related, but they are about different APIs and different kinds of documentation drift." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer GPU broadcast NoneType error is unrelated to the embedding reinitialization bug in post_init." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Both touch tokenizers, but one is save_pretrained metadata mismatch and the other is AutoTokenizer loading behavior." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Different tokenizer-loading failures with different root causes: repository tokenizer.json lookup vs Mistral regex patch crash." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Different regressions in different model stacks: processor/tokenizer API breakage vs Deepseek tokenizer output changes." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "No overlap beyond being unrelated issues; one is a pipeline bug, the other is a placeholder 'ADD THE DATA' report." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "A Python version compatibility issue is not the same as a generic dependency complaint." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Both mention loading problems, but one is environment/Python compatibility and the other is a model-specific load failure." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both are CI/repo hygiene issues, but they concern different files and different failure classes." + }, + { + "left": "issue:44462", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer-related, but one is repo file selection and the other is tokenization correctness for Deepseek." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Both involve multimodal templates/positioning, but the concrete bugs are different: assistant masks vs video temporal position ids." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "Completely different problems: FlashAttention failure on Ministral-3 vs OCR index error in Kosmos2.5." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batching shape bug is unrelated to a generic dependency issue." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Saving quantized models and loading dequantized models with offload are different code paths and failures." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "Different GLM components: MLA q_a_layernorm config precision issue vs torch.split return handling in a DSA indexer." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Both touch vision models, but one is a dummy Conv2d cleanup and the other is a Perceiver resolution bug." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Both mention embeddings/serialization, but one is device-dependent lm_head.weight serialization and the other is Gemma4 resize_token_embeddings behavior." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "'ADD THE DATA' is not a substantive bug report and does not match the chat-template tool-call crash." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Different attention-related failures, but not the same issue: model-specific FlashAttention regression vs compiled flex_attention on newer torch." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Both are loading-related, but one is an AutoTokenizer v5 issue and the other is an ESM2 model breakage affecting workflows." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Processor save_pretrained missing files is unrelated to Gemma-4 zero3 from_pretrained behavior." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 32, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:43122", + "issue:43262", + "issue:43299", + "issue:43352", + "issue:43450", + "issue:43525", + "issue:43643", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43761", + "issue:43784", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44188", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44291", + "issue:44295", + "issue:44297", + "issue:44336", + "issue:44361", + "issue:44373", + "issue:44496", + "issue:44521", + "issue:44589", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44749", + "issue:44779", + "issue:44987", + "issue:45250", + "issue:45362", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:44623|issue:44749", + "issue:43653|issue:45593", + "issue:44016|issue:45823", + "issue:43784|issue:45542", + "issue:44671|issue:44779", + "issue:44987|issue:45542", + "issue:44361|issue:45593", + "issue:43901|issue:43994", + "issue:43122|issue:43650", + "issue:44016|issue:44291", + "issue:43262|issue:44521", + "issue:43525|issue:43881", + "issue:43673|issue:43761", + "issue:44188|issue:44336", + "issue:44297|issue:45397", + "issue:43525|issue:43643", + "issue:43450|issue:44617", + "issue:42491|issue:43299", + "issue:44589|issue:45362", + "issue:41628|issue:43976", + "issue:43901|issue:44246", + "issue:44336|issue:44373", + "issue:44242|issue:45593", + "issue:43352|issue:45250", + "issue:16998|issue:22355", + "issue:44295|issue:45397", + "issue:44246|issue:44496", + "issue:41950|issue:44220" + ], + "prepared_review_unit_hash": "f449d541e497c7b30307b5f941d4f280b4c295c274c133e68920bfdb69664380", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35151, + "estimated_input_tokens": 8788, + "estimated_eval_tokens": 17832 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: it spans unrelated bugs in tokenizers, model loading, processors, docs, and CI. None of the soft pairs look like true duplicates; they are at best broad theme neighbors. For a single representative issue, the best fit is the open, detailed multimodal processor bug (#44521), but there is no strong canonical duplicate hub here.", + "confidence": 0.94, + "canonical_issue_reason": "#44521 is the most active and detailed issue in the set, with multiple inbound references and a concrete reproducible processor/chat-template bug; it is the closest thing to a cluster anchor, though the cluster overall is not a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "#44521 is the strongest issue candidate overall because it is open, specific, actionable, and sits in a theme that overlaps several other processor-related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Both mention processor/filtering performance, but one is a missing-file save_pretrained bug and the other is a slowdown regression; different symptoms and likely different code paths." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "Both involve auxiliary/special handling around model outputs, but one is a tokenizer special-token decode bug and the other is missing auxiliary losses when denoising is off; not the same bug." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax/docs issue versus Gemma4 device-map forward device mismatch; unrelated problems." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Import-time NameError in sentence-transformers integration versus TensorBoard/TensorFlow backend detection; different modules and failure modes." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "Both are v5 regressions affecting model behavior, but one is masked LM prediction drift and the other is Deepseek tokenizer output corruption; not the same concrete change." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Model loading failure for a specific repo versus missing TensorFlow backend handling; no shared underlying bug." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "Tokenizer task AttributeError versus missing aux losses in D-FINE; different tokenizer/model subsystems." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for text-classification pipeline versus nonsensical SigLIP model outputs; one is documentation, the other is model behavior." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenization differences across versions versus a vague non-technical issue title; no meaningful evidence of the same bug." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error versus init_empty_weights TypeError during model loading; unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both involve processors/chat templates, but one is audio sampling-rate defaulting and the other is multimodal assistant mask generation; different functionality and fixes." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Different config-field load failures for different models; similar class of error, not the same underlying model-specific issue." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Cache-related generation issue versus CLIPVision hidden_states regression; separate code paths." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "torch.compile attention-kernel branching bug versus ANSI codes in loading report; no overlap beyond both being utility/regression reports." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer class mismatch on save_pretrained versus Gemma-4 zero3 from_pretrained; different serialization/loading issues." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Both are configuration/loading problems, but one is a missing pad_token_id on a config class and the other is trust_remote_code dropping fields; distinct bugs." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Video processor batch shape bug versus Sam3Video OOM; one is a shape correctness issue, the other is memory usage." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both concern Qwen3 MoE models across versions, but one is LoRA compatibility on hf4.x/hf5.x and the other is base model loading failure in v5.0.0.dev0; not enough to treat as the same bug." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Storage deserialization error for Float8 tensors versus Qwen3.5 chat crash; unrelated failures." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Import error for AutoImageProcessor versus Python version incompatibility in Transformers 5.1.0; separate release/packaging issues." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Pipeline docs mismatch versus import latency regression; different concerns and fixes." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI escape codes in a loading report versus a wrong docstring for position_ids; both doc-like issues, but not the same artifact or defect." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Load-balancing loss omission in MoE versus D-FINE auxiliary-loss omission; superficially similar, but they affect different models and loss computations." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Nemotron-specific Flash Attention 2 unsupported error versus a generic Flash Attention 2 issue title; too vague to call duplicates." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "Model_max_length question for DeBERTa-V3 versus missing transformers.onnx module; unrelated." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "position_ids buffer access bug versus Gemma-4 zero3 loading issue; different runtime paths." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import slowness regression versus unrecognized model/config.json issue; no same code-path evidence." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification pipeline using image processors versus _torch_extract_fbank_features() bug; both are media-preprocessing related at a high level, but not the same issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 33, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36246", + "issue:42757", + "issue:42886", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43475", + "issue:43526", + "issue:43540", + "issue:43596", + "issue:43673", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44466", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:44964", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45375", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:36246|issue:42757", + "issue:36246|issue:44351", + "issue:44336|issue:44485", + "issue:43673|issue:44561", + "issue:43824|issue:43976", + "issue:43976|issue:44964", + "issue:44242|issue:44857", + "issue:44246|issue:44871", + "issue:45362|issue:45375", + "issue:44162|issue:45200", + "issue:44295|issue:44749", + "issue:44877|issue:45375", + "issue:44779|issue:45292", + "issue:45292|issue:45584", + "issue:45292|issue:45701", + "issue:45561|issue:45563", + "issue:44987|issue:45459", + "issue:43901|issue:45003", + "issue:36246|issue:43596", + "issue:43232|issue:44336", + "issue:45375|issue:45759", + "issue:43526|issue:45003", + "issue:43065|issue:43408", + "issue:44496|issue:45003", + "issue:44995|issue:45200", + "issue:43257|issue:45137", + "issue:43262|issue:44246", + "issue:43475|issue:43540", + "issue:42886|issue:45229", + "issue:44466|issue:45335" + ], + "prepared_review_unit_hash": "fe56816867694ea5634b4be2dcbd3aadd605d122cc52f2668ea357f26b79b432", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36708, + "estimated_input_tokens": 9177, + "estimated_eval_tokens": 18610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Loose cluster of mostly unrelated Transformers v5 regressions (imports, model loading, config handling, generation, and model-specific bugs). None of the soft pairs are strong enough to treat as duplicates, so no pair is accepted.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45003 is the most cross-cutting and infrastructure-oriented report in the set, centered on core loading/import behavior rather than a single model family.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45003 is the best representative of the cluster because it points to a broader core regression with wider impact than the more model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but one is Qwen2.5 VL image processor export and the other is a missing huggingface_hub symbol; different underlying failures." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing names from different modules/classes; no shared code-path beyond generic import failure." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI color leakage in loading_report and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Both touch generation/runtime behavior, but one is cache handling in chunked prefill and the other is a v5 API removal breaking trust_remote_code models; not the same bug." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Qwen2.5 VL import failure versus Python 3.9+/3.10+ compatibility breakage; different issues." + }, + { + "left": "issue:43976", + "right": "issue:44964", + "accept": false, + "reason": "Interpreter-version support problem and a specific multimodal model loading failure are not the same underlying defect." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Load-balancing loss omission and AMP/CUDA crash in another loss class are distinct training bugs." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import slowness and Gemma eos_token_id config mismatch are unrelated." + }, + { + "left": "issue:45362", + "right": "issue:45375", + "accept": false, + "reason": "Both mention Qwen, but one is chat runtime failure and the other is a missing config field; different code paths and symptoms." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 model breakage and Gemma 4 mm_token_type_ids defaulting are unrelated model-specific bugs." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Position_ids buffer access error and post-upgrade tokenization slowdown are different problems." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Strict config rejection for granite_speech is a different model/config issue than the Qwen3_5MoeVisionConfig field loss." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer correctness regression and resize_token_embeddings not updating output embeddings are separate behaviors." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize behavior and Whisper empty-transcription generation failure do not share a concrete bug." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "A resizing/tying bug and a broad tokenization-version change are not the same issue." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "Test xdist race on captured_info.txt and a stale warning in paged generate() are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure for a specific repo and tokenizer error masking from missing protobuf are different bugs." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mismatch for TextClassificationPipeline and unsafe sys.modules access are unrelated." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Qwen2.5 VL import error and DeepSpeed ZeRO3/BertModel index error are entirely different failure modes." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs update after sync_gpus and ANSI output formatting in loading_report are unrelated." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Missing Qwen3_5MoeVisionConfig field and failure to unwrap text_config in composite configs are both Qwen multimodal, but they are distinct config-handling bugs." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BEiT label reduction bug and sys.modules access bug are not the same underlying problem." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Both are SAM3-related, but one is a dummy Conv2d implementation detail and the other is a model-type warning; different defects." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model/config loading for a specific repo is not the same as unsafe sys.modules access." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "GlmMoeDsa stale cache crash and Gemma 4 token-type defaults are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Both involve DeepSpeed, but one is weight conversion/loading and the other is ZeRO3 deque underflow; not the same bug." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio processor sampling-rate defaulting and import slowness are unrelated." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "SAM3 vision encoder missing field and Qwen3OmniMoe video-input ValueError are different model-specific issues." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline cache loading for tokenizers and Gemma4 multi-GPU OOM are unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Serialization inconsistency of tied weights and resize_token_embeddings not propagating to decoder.embed_tokens are different embedding/weight-handling bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 34, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:41628", + "issue:42371", + "issue:42994", + "issue:43232", + "issue:43452", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43643", + "issue:43646", + "issue:43653", + "issue:43673", + "issue:43827", + "issue:43931", + "issue:44038", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44623", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:44977", + "issue:44995", + "issue:45003", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45230", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45459", + "issue:45478", + "issue:45561", + "issue:45563", + "issue:45588", + "issue:45600", + "issue:45656" + ], + "soft_pairs": [ + "issue:44995|issue:45588", + "issue:43653|issue:44162", + "issue:44368|issue:45563", + "issue:44368|issue:44977", + "issue:45397|issue:45656", + "issue:44060|issue:44077", + "issue:43673|issue:44734", + "issue:45003|issue:45561", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:44869|issue:45356", + "issue:44933|issue:45459", + "issue:44297|issue:44623", + "issue:43646|issue:44162", + "issue:44361|issue:44749", + "issue:43232|issue:43673", + "issue:43673|issue:43827", + "issue:43452|issue:45003", + "issue:28282|issue:30990", + "issue:44623|issue:45656", + "issue:42994|issue:43482", + "issue:44749|issue:45310", + "issue:44749|issue:45656", + "issue:42371|issue:45092", + "issue:43475|issue:43643", + "issue:43475|issue:45381", + "issue:44038|issue:44623", + "issue:45230|issue:45397", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:42994|issue:43525", + "issue:45375|issue:45478" + ], + "prepared_review_unit_hash": "7317290e78e7081ee57133e700b3f4691739c5b3eb3cdd33f6ed429d2aed85c8", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37273, + "estimated_input_tokens": 9319, + "estimated_eval_tokens": 18894 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a heterogeneous set of mostly unrelated issue reports, and every soft edge looks like a false positive rather than a true duplicate. No PRs are present, and no merge candidates should be accepted.", + "confidence": 0.88, + "canonical_issue_reason": "issue:45003 is the broadest core-framework bug in the set, but the overall cluster is too heterogeneous to represent a real duplicate group.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45003 is the best single representative because it targets a general runtime bug in core modeling utilities; still, it is not a strong duplicate hub.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Different failures: stale cache on second forward vs flash-attention None-aux crash." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer decode bug vs ESM2 model breakage; same broad area only." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Different warning paths: tied-weights config warning vs paged generate num_return_sequences warning." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "One is a warning about tied embeddings; the other is a flash-attention generation failure." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Zero3 from_pretrained loading issue vs optimizer stepping twice under deepspeed; not the same bug." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Tied-weights warning bug vs patchtsmixer post_init policy change; unrelated code paths." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Generation cache issue vs serve KV-cache tensor indexing crash; different concrete defects." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Unsafe sys.modules access vs xdist file race in testing utils; unrelated failures." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed deque underflow vs stale auto_mappings config reference; not the same underlying bug." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Shape mismatch loading Qwen3-VL model vs a warning about tied embeddings." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper timestamp decode crash vs tokenizer codec/regression handling; different subsystems." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Missing import from image_utils vs protobuf-error masking in tokenizers; unrelated." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Tokenizer save metadata mismatch vs processor save missing files; both save_pretrained, but different objects and failures." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Custom model init regression vs ESM2 broken model behavior; too broad to merge as duplicates." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "Tokenizer AttributeError on tasks vs generation slowdown after upgrade; different symptoms and code paths." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "sync_gpus generation kwargs bug vs missing cache in v5.0.0; related area but not the same defect." + }, + { + "left": "issue:43673", + "right": "issue:43827", + "accept": false, + "reason": "Generation cache bug vs docs still referencing removed pipeline(); code vs documentation." + }, + { + "left": "issue:43452", + "right": "issue:45003", + "accept": false, + "reason": "gguf_file loader breakage vs unsafe sys.modules access; unrelated mechanisms." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "PyTorch missing ImportError vs Sentence Transformers loading hang; both loading-related only at a very high level." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Processor save files issue vs deepspeed optimizer double-step; unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure vs Qwen2.5-GGUF loading failure; opposite directions and different failure modes." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "Data preprocessing slowdown vs Qwen3.5 Moe from_pretrained error; not the same bug." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "Filtering slowdown vs optimizer stepping twice; no shared underlying defect." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 API/settings guidance vs remote-code meta-init incompatibility; unrelated issues." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "Missing SAM3 vision field vs trust_remote_code field loss; both missing-fields themed, but different models and causes." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "SAM3 video attribute error vs Qwen2.5-VL position-id bug; distinct model families." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe v5 compatibility issue vs processor.save_pretrained missing files; unrelated." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "Generic bug report vs gemma-4 zero3 loading error; no concrete duplicate evidence." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "AutoImageProcessor import failure vs nonexistent image_utils import; similar import surface only, not same symbol or fix." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Mistral regex patch crash vs auto_docstring annotations crash; different decorators and failure points." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized saving failure vs Llama4Config missing pad_token_id; unrelated model/config bugs." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Missing config field silently dropped vs Qwen3.5-Moe from_pretrained error; related family only, not same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 35, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43475", + "issue:43704", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43901", + "issue:44038", + "issue:44060", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44373", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44661", + "issue:44734", + "issue:44792", + "issue:44964", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45561", + "issue:45600", + "issue:45712", + "issue:45812" + ], + "soft_pairs": [ + "issue:42673|issue:43704", + "issue:43475|issue:44661", + "issue:45310|issue:45375", + "issue:41628|issue:44351", + "issue:42831|issue:44222", + "issue:42222|issue:45200", + "issue:44222|issue:45310", + "issue:42994|issue:43824", + "issue:42175|issue:45712", + "issue:36010|issue:41628", + "issue:43377|issue:44242", + "issue:44038|issue:45310", + "issue:44496|issue:45561", + "issue:45561|issue:45600", + "issue:44964|issue:45137", + "issue:43901|issue:45561", + "issue:42898|issue:44568", + "issue:43232|issue:44792", + "issue:30990|issue:35141", + "issue:43232|issue:44188", + "issue:42898|issue:45812", + "issue:44188|issue:44373", + "issue:43784|issue:43824", + "issue:44623|issue:45310", + "issue:43278|issue:45137", + "issue:44734|issue:45103", + "issue:30333|issue:33290", + "issue:43723|issue:44568", + "issue:42898|issue:45356", + "issue:44060|issue:45125", + "issue:43874|issue:45092" + ], + "prepared_review_unit_hash": "2950dc2212edc2a628d59324f2ff3a7cf4408c6e58fd667c3aae26414d833dd7", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37034, + "estimated_input_tokens": 9259, + "estimated_eval_tokens": 18774 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous issue reports. The only strong duplicate signal is the Qwen3ForCausalLM VRAM leak pair, which matches exactly in title and is a good duplicate candidate, though the evidence here is still limited to the metadata/titles rather than full bodies.", + "confidence": 0.81, + "canonical_issue_reason": "issue:42673 is the best canonical issue because it is the fuller, more active report in the likely duplicate pair with issue:43704: the titles match exactly and both point to the same Qwen3ForCausalLM VRAM leak scenario.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42673 is the strongest issue candidate overall: it has the clearest duplicate match in the set and enough discussion/references to serve as the canonical landing spot for that likely duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact same title and a strong likely-duplicate signal for the same Qwen3ForCausalLM VRAM leak report, though the available evidence is limited to metadata." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "Different components and symptoms: a SAM 3 vision encoder attribute error versus a tokenizer/model-mapping failure." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Both involve Qwen3.5 MoE, but the reported failures differ: from_pretrained loading error versus a missing config field being dropped." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different exported symbols and likely different regressions." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Different failure modes: fine-grained FP8 accuracy issues versus FP8 save_pretrained/moe serialization." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Unrelated models and bugs: broken VitPose models versus Gemma 4 mm_token_type_ids defaults." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Related MoE/FP8 area, but not the same concrete code-path problem: save_pretrained bug versus from_pretrained loading error." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Quantized model saving failure is unrelated to an import error for Qwen2_5_VLForConditionalGeneration." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "TensorFlow backend omission for torch install is unrelated to leftover dummy PT classes leaking into dir() and check_repo." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Different import names and likely different top-level export regressions." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "MIMI padding-mask batching bug is unrelated to load-balancing loss not being added." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Both involve Qwen models, but one is a general Transformers 5.0 compatibility issue and the other is a specific Qwen3.5 MoE loading error." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Model loading/config error versus a pytest-xdist race in testing utils; unrelated." + }, + { + "left": "issue:45561", + "right": "issue:45600", + "accept": false, + "reason": "Testing race on captured_info.txt is unrelated to auto_mappings referencing removed Sam3LiteText configs." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Phi-4 multimodal load failure and a DeepSpeed ZeRO3 deque error are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:45561", + "accept": false, + "reason": "Doc mismatch for TextClassificationPipeline is unrelated to a pytest-xdist captured_info.txt race." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer regressions, but they concern different options and different model families." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs handling after sync_gpus is unrelated to a janus image-generation test failure." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence Transformers loading hang is unrelated to token embedding reinitialization on resize." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation sync_gpus kwargs handling and attention-kernel divergence under torch.compile are different code paths." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Different tokenizer regressions affecting different behaviors and model families." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Attention-kernel branching under torch.compile is unrelated to a docstring mismatch for position_ids." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Different import failures for different symbols; not the same underlying issue." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Processor save_pretrained missing files is unrelated to Qwen3.5 MoE from_pretrained loading failure." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift during evaluate is unrelated to DeepSpeed ZeRO3 deque popping." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "Serving KV-cache continuation crash and auto_docstring annotation crash are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLFlow job-state reporting bug is unrelated to AdaFactor OOM in DeepSpeed." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer loading issue in v5 and add_special_tokens BOS/EOS behavior are distinct bugs." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer regressions: clean_up_tokenization_spaces behavior versus Kimi-K2.5 codec handling." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Incorrect tied-weights warning and missing tensor-parallel plan are different Qwen3.5 MoE issues." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing image-processor method and old InternVL2 meta-init incompatibility are not the same bug." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The grouping is mostly grounded, but the positive Qwen3ForCausalLM pair is overstated. The packet supports a strong duplicate candidate because the titles match exactly, yet it does not establish an \"exact duplicate\" or prove the underlying bug is identical from the available evidence (the bodies are not shown, and the similarity signal is only moderate). The canonical/best-issue wording should stay conservative, e.g. \"likely duplicate\" or \"best duplicate candidate,\" rather than \"exact duplicate counterpart\" and \"same underlying bug.\"" + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 36, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42175", + "issue:42757", + "issue:42831", + "issue:42898", + "issue:43232", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43873", + "issue:43976", + "issue:44079", + "issue:44188", + "issue:44206", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44448", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44623", + "issue:44779", + "issue:44869", + "issue:44871", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45092", + "issue:45103", + "issue:45310", + "issue:45357", + "issue:45405", + "issue:45406", + "issue:45656", + "issue:45712", + "issue:45834" + ], + "soft_pairs": [ + "issue:42898|issue:44779", + "issue:45405|issue:45712", + "issue:42898|issue:44448", + "issue:44188|issue:44964", + "issue:43479|issue:44079", + "issue:44295|issue:45656", + "issue:44933|issue:45712", + "issue:42175|issue:44933", + "issue:43976|issue:44933", + "issue:44222|issue:44297", + "issue:43479|issue:44869", + "issue:44297|issue:45656", + "issue:44206|issue:45103", + "issue:42831|issue:44623", + "issue:44222|issue:44623", + "issue:41628|issue:42757", + "issue:30333|issue:36331", + "issue:43232|issue:45834", + "issue:43723|issue:44977", + "issue:30333|issue:34689", + "issue:43873|issue:44945", + "issue:44222|issue:44484", + "issue:44297|issue:45310", + "issue:28282|issue:30333", + "issue:44263|issue:45092", + "issue:30333|issue:35141", + "issue:44483|issue:45406", + "issue:44263|issue:44360", + "issue:44373|issue:44485", + "issue:44514|issue:45103", + "issue:43479|issue:43644", + "issue:44295|issue:44623", + "issue:44261|issue:45092", + "issue:43723|issue:44871", + "issue:45092|issue:45357" + ], + "prepared_review_unit_hash": "64db26f1a81c53289e37ca25c43062ffe2f871daa41af120f71dd4b42ec30553", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38016, + "estimated_input_tokens": 9504, + "estimated_eval_tokens": 19264 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No clear duplicate cluster emerges here: the items span unrelated issues across tokenization, model loading, training, config, imports, and save/load behavior. I would not select a canonical issue/PR, and none of the soft pairs look like the same underlying bug or change.", + "confidence": 0.95, + "canonical_issue_reason": "No clear canonical issue; the items cover distinct regressions and API mismatches rather than one duplicate bug.", + "canonical_pr_reason": "No PRs are present in this set.", + "best_issue_reason": "No single issue is a better global representative than the others; choosing one would be arbitrary.", + "best_pr_reason": "No PRs are present, so there is no best PR candidate.", + "soft_edge_verdicts": [ + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both involve tokenization behavior changes in v5, but one is about clean-up behavior and the other is a Deepseek tokenizer regression; different failure modes and code paths." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "One is a dependency-version bump problem, the other is leftover dummy class cleanup; unrelated issues." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Different tokenizer/output regressions: clean-up text handling vs Pegasus model output differences across v4/v5." + }, + { + "left": "issue:44188", + "right": "issue:44964", + "accept": false, + "reason": "Attention-kernel divergence under torch.compile is unrelated to a Phi-4 multimodal loading failure." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Config initialization for Phi4 multimodal and ModelOutput key assignment are separate bugs in different components." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Reading a registered buffer and double optimizer stepping with deepspeed are different runtime problems." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Both touch import surface area, but one is a missing image_utils import and the other is dummy PT class cleanup." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "TensorFlow backend packaging and a missing image_utils import are not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version compatibility and an import export issue are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "Both mention save_pretrained, but one is FP8 MoE serialization and the other is tokenizer metadata mismatch; different fixes." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Phi4 config defaults and Whisper timestamp decoding are unrelated subsystems." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save_pretrained metadata and deepspeed optimizer stepping do not describe the same defect." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "A feature-extractor regression and an auto-docstring crash are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FP8 accuracy issues and processor.save_pretrained missing files are different problems." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Both involve save_pretrained, but one is about MoE FP8 saving and the other about missing processor files." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Two separate import errors from different packages/modules; not the same underlying change." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLFlow reporting on failed jobs and Trainer.compute_loss signature breakage are unrelated training issues." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs update after sync_gpus and Kosmos2.5 OCR index errors are different code paths." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading failure and flash-attention generation issues are distinct model/runtime regressions." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "MLFlow job-state reporting and Llama 3.2 Vision model loading are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization/offloading behavior and pipeline-parallel output correctness are different problems." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE save_pretrained and the 50GB shard-size question are not the same bug." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer config serialization and Qwen3.5 MoE from_pretrained errors are different issues." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "ImportError for missing PyTorch and MLFlow reporting after failed jobs are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "A torch.split return-value issue and a meta-initialization compatibility regression are different model-loading bugs." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Training-job reporting and embedding reinitialization after resize are unrelated." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "API request rejection at /v1/chat/completions and Gemma4Processor missing _tokenizer are distinct failures." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "The DSA indexer split-values bug and the DSA indexer ReLU discussion are not the same concrete defect." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "A wrong docstring and a RoPE implementation discussion are not the same bug/change." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Qwen2_5_VLProcessor batched chat-template crash and an auto-docstring AttributeError are unrelated." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Phi4 multimodal config defaults and junk-filled non-persistent buffers are different regression classes." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Position_ids buffer access and missing processor save files are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "MLA q_a_layernorm epsilon precision and old InternVL2 meta-init incompatibility are separate model issues." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading in v5 and Gemma eos_token_id inconsistency are different tokenizer/model config problems." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Meta-initialization incompatibility and Qwen3.5 visual-encoder save_pretrained keys are unrelated regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 37, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30990", + "issue:33357", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43066", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43475", + "issue:43479", + "issue:43576", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44442", + "issue:44514", + "issue:44568", + "issue:44704", + "issue:44779", + "issue:44913", + "issue:44945", + "issue:45245", + "issue:45278", + "issue:45290", + "issue:45310", + "issue:45593", + "issue:45600", + "issue:45753" + ], + "soft_pairs": [ + "issue:30990|issue:38175", + "issue:43479|issue:44913", + "issue:41628|issue:43824", + "issue:22355|issue:28282", + "issue:42886|issue:42994", + "issue:39401|issue:44568", + "issue:42831|issue:45310", + "issue:44263|issue:44373", + "issue:44945|issue:45753", + "issue:42757|issue:45278", + "issue:42831|issue:44038", + "issue:43576|issue:43784", + "issue:42886|issue:43066", + "issue:43232|issue:45593", + "issue:42371|issue:44263", + "issue:43756|issue:44060", + "issue:44117|issue:44704", + "issue:30990|issue:33357", + "issue:42907|issue:44945", + "issue:44704|issue:45290", + "issue:43122|issue:44514", + "issue:44295|issue:44297", + "issue:43232|issue:45245", + "issue:43723|issue:44442", + "issue:43723|issue:44779", + "issue:41628|issue:45278", + "issue:43784|issue:45600", + "issue:42907|issue:43937", + "issue:43408|issue:43475", + "issue:44261|issue:44373" + ], + "prepared_review_unit_hash": "fe2aeea8e52727ac6501246d09db897accf360a5a4009cdefb296ffb7fb87204", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 35653, + "estimated_input_tokens": 8914, + "estimated_eval_tokens": 18084 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is a loose cluster of mostly unrelated Transformers bugs: tokenizer/import regressions, model-specific config issues, generation bugs, and save/load failures. There is no strong duplicate pair; most soft edges are only superficially similar (same subsystem or same error class) but not the same underlying defect.", + "confidence": 0.74, + "canonical_issue_reason": "issue:45278 is the broadest umbrella-style report in the set ('Many import errors after update from 4.57.0 to 5.5.0') and best matches the cluster\u2019s dominant theme of import/load regressions.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best global representative because it is recent, open, and broad enough to cover multiple import-related symptoms, even though the overall cluster is heterogeneous.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Different bugs: one is Sentence Transformers hanging during load, the other is a zero-probability inference issue for a specific SigLIP2 model." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Both are config-related, but they affect different model classes and different fields; no sign of the same underlying bug." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but they are for different missing symbols and likely different export paths/regressions." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Unrelated missing-module vs missing-dependency errors: transformers.onnx is a module import issue, while AutoModel/PyTorch is an environment dependency issue." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline tokenizer cache loading and quantized model saving are different code paths and failure modes." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Different tokenizer regressions affecting different models and behaviors (offset mapping vs special-token insertion)." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "Accuracy degradation in FineGrainedFP8 is not the same defect as a Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "One is a runtime tensor-splitting bug; the other is a docstring-only issue." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Different generation failures: pipeline-parallel output corruption vs an infinite loop on a specific image/model scenario." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "Related to imports, but one is a specific missing hub symbol while the other is a broad multi-import regression; not enough evidence of the same bug." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Accuracy issue and model-loading bug are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "A broken CLI environment command is unrelated to a NameError while importing sentence-transformers." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Tokenizer cache offline loading is unrelated to tokenizer decoder-type metadata in v5." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation state-update bug and D-FINE auxiliary-loss bug are different subsystems and symptoms." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 configuration warning/behavior issue is unrelated to a torch.split return-value bug." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Different model-specific architecture bugs: RoPE-layer dropping vs a tied-weights warning involving Qwen3-Next." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Tokenizer mapping fallback bug and AutoProcessor kwargs forwarding bug are different loading-path issues." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Loading hang and MacOS bus error are different failure modes on different models." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Quantized/dequantized model saving failure is unrelated to incorrect generation output under pipeline parallelism." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor file lookup/kwargs handling is unrelated to chat-template crashes with tool-call assistant messages." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer behavior changes and processor chat-template batching crashes are different bugs." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Position_ids buffer access and tokenizer_class metadata mismatch are unrelated serialization/runtime issues." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Generation kwargs handling and category cardinality limits are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Both concern AutoTokenizer loading, but one is a broad v5 regression and the other is a model-specific tokenizer failure; not clearly the same bug." + }, + { + "left": "issue:43723", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer loading failure and incorrect tokenization results are related only at a high level, not the same concrete defect." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-related, but the specific missing AutoImageProcessor symbol is not enough to treat it as the same underlying issue as the broad import-error report." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Importing sentence-transformers with a NameError is unrelated to a CI break from stale auto_mappings references." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Quantized-model saving and invalid GenerationConfig are different bug classes." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "A model-type warning during instantiation is not the same as a missing attribute error in SAM 3 Video." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "Precision/config discussion about rms_norm_eps is unrelated to a docstring issue for position_ids." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 38, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29127", + "issue:30990", + "issue:36296", + "issue:39401", + "issue:42222", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43441", + "issue:43452", + "issue:43493", + "issue:43784", + "issue:43824", + "issue:43825", + "issue:43874", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44360", + "issue:44485", + "issue:44488", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44779", + "issue:44829", + "issue:44936", + "issue:44964", + "issue:44977", + "issue:45200", + "issue:45216", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45753" + ], + "soft_pairs": [ + "issue:44360|issue:44485", + "issue:43122|issue:44521", + "issue:44625|issue:44829", + "issue:43116|issue:45200", + "issue:29127|issue:30990", + "issue:42907|issue:44964", + "issue:43122|issue:44779", + "issue:44038|issue:44297", + "issue:42907|issue:43452", + "issue:39401|issue:44488", + "issue:44038|issue:44295", + "issue:43824|issue:44351", + "issue:36296|issue:43116", + "issue:44038|issue:44222", + "issue:39401|issue:44521", + "issue:45216|issue:45478", + "issue:42757|issue:44351", + "issue:43066|issue:44779", + "issue:22355|issue:28218", + "issue:42907|issue:44222", + "issue:43122|issue:44977", + "issue:43992|issue:44704", + "issue:43784|issue:45446", + "issue:43937|issue:44485", + "issue:42222|issue:43441", + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:43493|issue:45753", + "issue:42831|issue:45753", + "issue:44075|issue:44936", + "issue:44038|issue:45478", + "issue:43116|issue:43825", + "issue:44222|issue:45478", + "issue:43116|issue:43493", + "issue:43937|issue:45563" + ], + "prepared_review_unit_hash": "cd7ac97c73b62507b4b1eb888a426dd84fc8609ba3149eee6769dd643da71ebc", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37059, + "estimated_input_tokens": 9265, + "estimated_eval_tokens": 18786 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is highly heterogeneous: most items are unrelated Transformers bugs spanning tokenization, model loading, export/save paths, attention kernels, and trainer behavior. None of the soft-similarity pairs are safe duplicates, and there are no PRs to choose from.", + "confidence": 0.79, + "canonical_issue_reason": "No single issue is a clear canonical for the whole set; the items span many unrelated bug classes, so collapsing them into one duplicate cluster would be unsafe.", + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must stand in for the mixed set, issue 43122 is the broadest regression-style report, but it still only represents a narrow tokenizer subset and does not unify the other topics.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "DSA/ReLU discussion and GLM-5 RoPE implementation are unrelated model-internal issues." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Tokenizer regression vs multimodal assistant_mask bug; different code paths and symptoms." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "num_labels propagation and flash_attention_3 degenerate training are distinct bugs." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Example-script multi-label output issue vs Gemma 4 token-type defaulting; not the same problem." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading hang are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Saving dequantized Ministral/Devstral models is not the same as loading Phi-4 multimodal instruct." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both mention tokenizer behavior in v5, but they are different model-specific regressions." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe load/runtime bug and tokenizer_class save metadata mismatch are different issues." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Different failure modes: dequantized save_pretrained vs gguf_file breaking from_pretrained." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 offset_mapping bug and sleng-bert load failure are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Qwen3-VL-Moe bug and position_ids buffer access error are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and different modules." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor parallel training bug and example-script classification output bug are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Both touch Moe models, but one is a load/runtime regression and the other is FP8 save_pretrained behavior." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Offset_mapping regression and multimodal chat-template assistant masks are different tokenizer features." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 and v5.4.0, but one is save_pretrained corruption and the other is from_pretrained failure." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Different import/export regressions from different packages and symbols." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer decoder-type regression and Deepseek tokenization regression are not the same concrete bug." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "Missing transformers.onnx import and extra-space tokenization are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both involve saving models, but the model families and serialization failures differ." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer regression vs Qwen3.5 flash-attention generation bug; different path and symptom." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "UMT5Encoder weight-loading and AutoProcessor cached_file kwargs are unrelated from_pretrained issues." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import NameError and flex_attention version-check bug are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "Invalid GenerationConfig and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "VitPose model breakage and Ministral flash-attention failure are unrelated model-specific bugs." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 behavior setting guidance and missing image-patch API are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version incompatibility and flex_attention import version check are different compatibility bugs." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "SigLIP2 discrepancy and Qwen3_5 infinite loop on one image are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue and Qwen3_5 infinite loop are unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "SGD argument handling and train/evaluate lifecycle failure are unrelated trainer/optimizer bugs." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen model families and different from_pretrained failures; not the same bug." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Example-script classification behavior and pipeline translation error messaging are unrelated." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Multi-label example output bug and SigLIP2 implementation discrepancy are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "Invalid GenerationConfig and stale num_return_sequences warning are unrelated generate-path issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 39, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42673", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43122", + "issue:43381", + "issue:43408", + "issue:43421", + "issue:43450", + "issue:43577", + "issue:43673", + "issue:43742", + "issue:43827", + "issue:43937", + "issue:43986", + "issue:44075", + "issue:44117", + "issue:44291", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44496", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45081", + "issue:45083", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45405", + "issue:45446", + "issue:45464", + "issue:45542", + "issue:45588", + "issue:45656" + ], + "soft_pairs": [ + "issue:43064|issue:43673", + "issue:45083|issue:45446", + "issue:38617|issue:45278", + "issue:39401|issue:44779", + "issue:33453|issue:39401", + "issue:44117|issue:45588", + "issue:22355|issue:29127", + "issue:43381|issue:44945", + "issue:43827|issue:45446", + "issue:43937|issue:44977", + "issue:45405|issue:45446", + "issue:43450|issue:43986", + "issue:42673|issue:45072", + "issue:44117|issue:45081", + "issue:38617|issue:41628", + "issue:39401|issue:43421", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:44291|issue:45071", + "issue:42222|issue:45542", + "issue:44484|issue:45310", + "issue:43937|issue:44496", + "issue:42175|issue:42222", + "issue:43408|issue:43742", + "issue:44483|issue:45464", + "issue:44075|issue:45656", + "issue:44964|issue:45278", + "issue:43012|issue:43577", + "issue:43066|issue:43122" + ], + "prepared_review_unit_hash": "2724faf083c36c37dfebc72192d733073918af088bbbf921c89cdf7902c03e8d", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36357, + "estimated_input_tokens": 9090, + "estimated_eval_tokens": 18436 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a heterogeneous cluster of mostly unrelated Transformers issues. A few share broad themes like tokenization, import regressions, or dtype/backend problems, but none of the soft pairs look like the same underlying bug or change. No PRs are present.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the broadest umbrella-style report in the set (many import errors after upgrading 4.57.0 -> 5.5.0), so it is the most plausible central tracker, though it still does not match most other items as a duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Different failures: FSDP2/PEFT optimizer-state corruption vs GenerationMixin cache missing during chunked prefill." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Different code paths: qwen3_omni_moe helper behavior vs flex_attention import/version check." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "One is a specific missing symbol import; the other is a broad collection of import errors after upgrade." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer bugs, but for different models and different symptoms: offset_mapping vs incorrect tokenization output." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Tokenizer loading regression and wrong offset mapping are distinct failures with different affected code paths." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES None handling is unrelated to a flash_attention crash on s_aux=None." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Missing transformers.onnx import and layoutlmv3 error-message clarity are unrelated issues." + }, + { + "left": "issue:43381", + "right": "issue:44945", + "accept": false, + "reason": "Gradient checkpointing in eval mode and incorrect output under pipeline parallelism are different bugs." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing pipeline() and a PyTorch version check bug are not the same change or bug." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GenerationConfig validation failure and Qwen3.5 flash-attention generation issues are different problems." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "PEFT dependency version bump and flex_attention import gating are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video processor shape bug and missing-torchvision processor crash are different layers of the video stack." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in multi-threaded dataloaders is unrelated to bfloat16 dtype mismatches in inference." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping None handling and _patch_mistral_regex backend_tokenizer crash are separate tokenizer bugs." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different missing names and different failure causes." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Wrong offset mapping and runtime post-processor update behavior are different tokenizer features and bugs." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Missing attention projections in qwen3next and Qwen3.5 from_pretrained errors are distinct model-loading/model-definition issues." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "Flash-attention training degeneration and incorrect save_pretrained checkpoint contents are unrelated behaviors." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights argument mismatch and PretrainedConfig type checking regression are different API breakages." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "Broken vitpose models and missing TensorFlow backend with tensorboard-only install are unrelated." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "A question about max_shard_size is not the same as a Qwen3.5-Moe from_pretrained failure." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "Invalid GenerationConfig and unrecognized model config are different config-loading errors." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "TensorFlow not included in a torch-only install and broken vitpose models are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "sam3_video/sam3_tracker warning and MobileLLM key error are different model-loading problems." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both involve chat/completions, but one is a general API rejection and the other is a Qwen3.5 streaming inference failure." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "SGD args ignored and optimizer.step() called twice under deepspeed are different optimizer bugs." + }, + { + "left": "issue:44964", + "right": "issue:45278", + "accept": false, + "reason": "Phi-4 multimodal load failure is not the same bug as a broad upgrade-wide import error regression." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "A bfloat16 compile warning and Blip2 dtype staying float32 are distinct dtype-handling issues." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Wrong tokenizer decoder type and changed tokenization output across versions are related broadly, but not the same concrete bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 40, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:38617", + "issue:41628", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42757", + "issue:42831", + "issue:43012", + "issue:43064", + "issue:43097", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43577", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44704", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:44987", + "issue:45071", + "issue:45103", + "issue:45245", + "issue:45341", + "issue:45375", + "issue:45459", + "issue:45478", + "issue:45542", + "issue:45588" + ], + "soft_pairs": [ + "issue:42371|issue:44261", + "issue:38617|issue:44220", + "issue:43874|issue:44261", + "issue:44410|issue:45478", + "issue:44484|issue:45478", + "issue:42222|issue:45459", + "issue:43097|issue:44493", + "issue:44263|issue:44485", + "issue:43012|issue:43408", + "issue:43441|issue:44829", + "issue:41628|issue:45071", + "issue:45071|issue:45542", + "issue:42371|issue:42831", + "issue:42673|issue:44977", + "issue:42673|issue:43906", + "issue:43931|issue:44038", + "issue:44117|issue:44987", + "issue:43097|issue:43452", + "issue:43335|issue:45071", + "issue:43976|issue:44945", + "issue:43986|issue:44484", + "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:44829|issue:45245", + "issue:38617|issue:42757", + "issue:43064|issue:44315", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "issue:44704|issue:45103", + "issue:43097|issue:45588", + "issue:44062|issue:44117", + "issue:44038|issue:44410", + "issue:42673|issue:43577", + "issue:44964|issue:45071", + "issue:43931|issue:44410", + "issue:44261|issue:44485", + "issue:44964|issue:45341" + ], + "prepared_review_unit_hash": "75b45e90a60991d0555d8bc0cc7300d291b1ccc62fe0d0ea1ccda5d34eeb0b21", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 37, + "serialized_chars": 38778, + "estimated_input_tokens": 9695, + "estimated_eval_tokens": 19646 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose mix of unrelated Transformers bug reports and regressions. The soft-similarity links are generally superficial, sharing only broad terms like import errors, Qwen/GLM model names, or flash-attention, but not the same concrete failure mode or code path.", + "confidence": 0.85, + "canonical_issue_reason": "No single true duplicate stands out; issue 45478 is the best representative because it is a concrete, reproducible v5.4.0 regression with a specific model and loading path.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45478 is the strongest global representative: it names the affected version, model family, and failure surface clearly, making it the most actionable anchor for the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API/settings warning vs. MLA q_a_layernorm precision bug; different root causes." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "ImportError for layer_type_validation vs. audio feature extraction issue; unrelated modules." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Missing image-patch method in GLM46V processor vs. RMS norm epsilon precision issue; different defects." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Missing projections in qwen3next layer 0 vs. Qwen3.5 MoE from_pretrained failure; different model/code paths." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "save_pretrained shard-size question vs. model loading regression; not the same bug." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "VitPose breakage vs. protobuf-hidden tokenizer errors; unrelated failures." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Removed tie_embeddings API vs. unexpected position-id key warnings; only loosely related to configs." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "GlmMoeDsaIndexer torch.split behavior vs. GLM-5 RoPE implementation; different code paths." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "bfloat16 compilation warning vs. sam3 model-type warning; different symptoms." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "FlashAttention load failure on Ministral-3 vs. degenerate training with flash_attention_3; not the same issue." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "AutoImageProcessor import error vs. PretrainedConfig type-checking regression; unrelated." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "Config type-checking breakage vs. missing TensorFlow backend error; different areas." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 behavior settings vs. FineGrainedFP8 accuracy issue; both precision-related but distinct." + }, + { + "left": "issue:42673", + "right": "issue:44977", + "accept": false, + "reason": "VRAM leak in dataloader threads vs. Qwen3.5 flash-attention generation bug; different failures." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "VRAM leak report vs. isolated reproduction of another issue; not the same bug." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Qwen3-VL-30B weight-shape mismatch vs. Qwen3-VL-Moe bug; same family, different defect." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None handling vs. physical-intelligence/fast load failure; unrelated code paths." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Removed tie_embeddings API vs. gguf_file load breakage; different loading problems." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug vs. PretrainedConfig type-checking regression; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version compatibility break vs. pipeline parallelism output corruption; different issues." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "AutoProcessor crash without torchvision vs. shard-size question; no overlap in defect." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "sam3 model-type warning vs. tie_word_embeddings warning in Qwen3.5 LoRA; different configs/models." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Missing image-patch helper vs. torch.split return-value issue; only both are GLM-adjacent." + }, + { + "left": "issue:44829", + "right": "issue:45245", + "accept": false, + "reason": "FlashAttention training collapse vs. category-count ceiling error; unrelated." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Different import errors from different missing names/modules; not duplicates." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "FSDP2+PEFT optimizer-state bug vs. Liger Kernel not applied with model_init; distinct training stack problems." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "qwen3next missing projections vs. missing deepstack_visual_indexes field; different model configs." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "layer_type_validation import error vs. HybridCache import error; separate missing symbols." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "AutoProcessor kwargs forwarding bug vs. auto_docstring future-annotations crash; different subsystems." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "tie_embeddings API removal vs. flash_attention sink-less-model AttributeError; unrelated." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken special-arg TypeError vs. tokenizer-mapping None handling; different tokenizer bugs." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL-Moe bug vs. qwen3next missing projections; same broad family only, not same defect." + }, + { + "left": "issue:42673", + "right": "issue:43577", + "accept": false, + "reason": "VRAM leak in threaded dataloading vs. Blip2 dtype staying float32; unrelated." + }, + { + "left": "issue:44964", + "right": "issue:45071", + "accept": false, + "reason": "Phi-4 multimodal load failure vs. PretrainedConfig typing regression; different problems." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL-30B shape mismatch vs. qwen3next layer-0 projection omission; distinct model-loading failures." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "RMS norm epsilon precision bug vs. GLM-5 RoPE implementation; different code paths." + }, + { + "left": "issue:44964", + "right": "issue:45341", + "accept": false, + "reason": "Model loading failure vs. a testing_utils bug; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 41, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36683", + "issue:38617", + "issue:42617", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43299", + "issue:43381", + "issue:43475", + "issue:43502", + "issue:43526", + "issue:43550", + "issue:43618", + "issue:43761", + "issue:43824", + "issue:43825", + "issue:43867", + "issue:43873", + "issue:43901", + "issue:43906", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44117", + "issue:44230", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44484", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:45216", + "issue:45290", + "issue:45341", + "issue:45372", + "issue:45381", + "issue:45561", + "issue:45588", + "issue:45753", + "issue:45859" + ], + "soft_pairs": [ + "issue:43502|issue:43992", + "issue:43986|issue:44117", + "issue:45341|issue:45859", + "issue:43097|issue:43873", + "issue:43066|issue:43906", + "issue:43986|issue:45290", + "issue:45341|issue:45561", + "issue:43986|issue:45372", + "issue:43097|issue:43901", + "issue:43986|issue:45341", + "issue:42617|issue:45341", + "issue:43825|issue:44655", + "issue:45341|issue:45588", + "issue:43992|issue:44484", + "issue:43012|issue:43550", + "issue:43208|issue:43550", + "issue:43012|issue:44368", + "issue:42886|issue:43381", + "issue:42907|issue:45753", + "issue:42907|issue:44655", + "issue:43208|issue:43526", + "issue:44483|issue:44514", + "issue:43012|issue:44683", + "issue:42757|issue:43824", + "issue:38617|issue:43502", + "issue:44483|issue:45290", + "issue:43618|issue:43761", + "issue:44038|issue:44230", + "issue:43299|issue:43867", + "issue:43064|issue:44380", + "issue:44483|issue:45381", + "issue:43901|issue:44655", + "issue:36683|issue:43475", + "issue:43867|issue:45216", + "issue:42994|issue:44655" + ], + "prepared_review_unit_hash": "dcc5aa4a013feee77bf589a5ba6dde21fc6941b9e3b81b35d6bc689dd9b548d5", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37412, + "estimated_input_tokens": 9353, + "estimated_eval_tokens": 18962 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a heterogeneous set of Transformer issues with only superficial keyword overlap. The proposed soft pairs do not look like the same underlying bug or change; they span unrelated import errors, save/load regressions, processor crashes, training failures, and compile/runtime warnings.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue stands out: the set is not a coherent duplicate cluster, and the soft pairs are mostly unrelated by code path.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue here is a good global representative for dedupe; the items are too diverse and none of the soft pairs match the same concrete defect.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Both are loading-related, but one is a local_files_only network request bug and the other is a missing embed_tokens.weight in UMT5Encoder; different code paths." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Video AutoProcessor import handling and tokenizer mapping fallback are unrelated failures." + }, + { + "left": "issue:45341", + "right": "issue:45859", + "accept": false, + "reason": "A testing utility bug and a Qwen3_5 rotary embedding offload issue are different subsystems." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Removed tie_embeddings_and_encoder_decoder and quantization offloading behavior are not the same bug." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Wrong tokenizer decoder type and an isolated reproduction issue are not the same defect." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor video-model import failure and chat template crashing on tool-call messages are separate code paths." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Testing utils race conditions and xdist capture are related only at a broad testing level, not the same bug." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Missing torchvision in AutoProcessor loading and Gemma 4 processor import breakage are different dependency issues." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "A removed model config API and stale pipeline docs about return_all_scores are unrelated." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Video AutoProcessor loading and a testing_utils bug do not share a concrete failure path." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "3d_parallel.py failure and a testing utils issue are unrelated." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline translation-message behavior and saving Pipeline objects are different problems." + }, + { + "left": "issue:45341", + "right": "issue:45588", + "accept": false, + "reason": "Testing utilities and flash_attention sink-less-model crash are unrelated." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing embed_tokens weight loading and save_pretrained shard-size question are not the same issue." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "A bfloat16 compile warning and Bamba SDPA compile failure are distinct compiler/backends problems." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training bugs and Bamba torch.compile SDPA failure are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "A PyTorch warning during compile and a tie_word_embeddings warning in Qwen3.5 are different warnings with different causes." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline tokenizer cache loading and gradient checkpointing in eval mode are separate behaviors." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Saving dequantized models and a Qwen3_5 infinite-loop generation bug are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Model dequantization save failures and pipeline save_pretrained failures are different save paths." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs and BeitImageProcessorFast label reduction are unrelated." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "OpenAI-compatible chat/completions routing and Qwen2.5-VL chat template batching are not the same bug." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "Generic compile warning and compiled flex_attention failure on newer torch are different failures." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Missing is_offline_mode and missing Qwen2_5_VLForConditionalGeneration are separate import regressions." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Missing layer_type_validation and unexpected API requests with local_files_only are unrelated." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Chat/completions request rejection and assistant tool-call template crash are different layers of the stack." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both are CLIP-related, but one is attentions missing from CLIPOutput and the other is hidden_states missing from CLIPVisionModel.forward; not the same concrete bug." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Qwen3/VL loading issues and fp8 support request are not duplicates." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3.5-VL MoE loading regression and state_dict-sorted load_model error are different load-time bugs." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption and GPT2 attention scaling with SDPA/FlashAttention are unrelated." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "OpenAI API request rejection and Qwen2.5-VL video vision_position_ids are different bugs." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Documentation mismatch for return_all_scores and inability to save Pipeline objects are unrelated." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config missing vocab_size and SAM 3 Video missing fpn_position_embeddings are different attribute regressions." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "State-dict ordering load error and Qwen3.5 save_pretrained regression are both save/load themed but not the same defect." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model save failure and Pipeline save_pretrained failure are different save code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 42, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36010", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42757", + "issue:42890", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43299", + "issue:43352", + "issue:43441", + "issue:43525", + "issue:43575", + "issue:43618", + "issue:43756", + "issue:43867", + "issue:43881", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44077", + "issue:44117", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44263", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44484", + "issue:44485", + "issue:44492", + "issue:44655", + "issue:44855", + "issue:44938", + "issue:45216", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45479", + "issue:45561", + "issue:45753" + ], + "soft_pairs": [ + "issue:43352|issue:43937", + "issue:43066|issue:45381", + "issue:36010|issue:42757", + "issue:43756|issue:44485", + "issue:44220|issue:44655", + "issue:44263|issue:45440", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:43906|issue:45753", + "issue:36683|issue:44242", + "issue:36683|issue:43881", + "issue:43299|issue:45753", + "issue:43352|issue:43976", + "issue:43441|issue:44380", + "issue:43352|issue:44380", + "issue:43992|issue:45310", + "issue:44380|issue:45479", + "issue:43867|issue:45375", + "issue:41669|issue:44246", + "issue:43352|issue:45478", + "issue:43618|issue:44380", + "issue:43064|issue:44492", + "issue:44355|issue:44855", + "issue:36683|issue:44117", + "issue:42890|issue:45561", + "issue:43097|issue:43352", + "issue:43867|issue:45357", + "issue:43976|issue:44938", + "issue:43992|issue:45478", + "issue:44360|issue:45440", + "issue:43064|issue:44655", + "issue:36296|issue:43575", + "issue:44077|issue:44380", + "issue:43867|issue:44484" + ], + "prepared_review_unit_hash": "eb96307c0f8904c7e3d917679a011b40f7f6c099a610a4bb307a75d038d78083", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 36867, + "estimated_input_tokens": 9217, + "estimated_eval_tokens": 18690 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous bug reports across unrelated models/features. The only plausible duplicate-like pair is the import-time slowdown reports (41669/44246); the rest share at most superficial keywords like model names, RoPE, or FlashAttention and are not the same concrete defect.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Different models and different failures: FlashAttention 2 unsupported vs invalid GenerationConfig." + }, + { + "left": "issue:43066", + "right": "issue:45381", + "accept": false, + "reason": "Both involve Qwen, but one is tokenizer decoder type and the other is video position IDs; different bugs." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Separate import errors from different packages/symbols, not the same missing-name regression." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Both mention RoPE, but they concern different models and different implementation defects." + }, + { + "left": "issue:44220", + "right": "issue:44655", + "accept": false, + "reason": "Unrelated areas: fbank feature extraction vs saving Pipeline objects." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "Different model/code paths: GlmMoeDsaIndexer split behavior vs DeepseekV3MoE divergence." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Same symptom class, but different configs, models, and missing fields." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIPOutput attentions omission is unrelated to Qwen3.5 save_pretrained checkpoint corruption." + }, + { + "left": "issue:43906", + "right": "issue:45753", + "accept": false, + "reason": "One is a reproduction of an older issue; the other is an infinite-loop bug for a specific image in Qwen3_5." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3 config attribute error vs MoE load-balancing loss computation; different defects." + }, + { + "left": "issue:36683", + "right": "issue:43881", + "accept": false, + "reason": "Different models and failure modes: Gemma3 config missing field vs glm-4v-9b loading failure." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Both are Qwen-family issues, but one is a loading regression and the other is a model-generation infinite loop." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "FlashAttention support issue vs Python-version compatibility issue." + }, + { + "left": "issue:43441", + "right": "issue:44380", + "accept": false, + "reason": "Different attention backends and different code paths; not the same model bug." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "FlashAttention support for Nemotron is unrelated to GPT2 attention scaling being ignored." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different models and loaders: UMT5Encoder missing weights vs Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention-scaling regression is unrelated to single-label classification zero-loss behavior." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "Generic state_dict loading error vs a missing Qwen3_5MoeVisionConfig field; not the same bug." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "Both describe Transformers import-time slowdown; one is a specific cause report and the other a broader symptom report." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "Distributed training optimizer-state bug vs a cache-strategy typo." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Compiled-file import errors and a Python 3.13 torch.jit.parse indentation problem are not the same failure." + }, + { + "left": "issue:36683", + "right": "issue:44117", + "accept": false, + "reason": "Missing Gemma3Config field vs tokenizer mapping returning None; unrelated." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Test flakiness from missing set_seed and xdist file races are different issues." + }, + { + "left": "issue:43097", + "right": "issue:43352", + "accept": false, + "reason": "API removal warning vs FlashAttention support bug; unrelated." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "Both concern Qwen3.5 serialization, but one is a generic sorted-state_dict load error and the other is incorrect visual encoder keys on save; not clearly the same bug." + }, + { + "left": "issue:43352", + "right": "issue:45478", + "accept": false, + "reason": "Same family name but different Qwen3.5 MoE import error vs Nemotron FlashAttention support." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA ReLU absence in indexer is unrelated to DeepseekV3MoE divergence." + }, + { + "left": "issue:43064", + "right": "issue:44655", + "accept": false, + "reason": "Optimizer-state corruption during training vs inability to save Pipeline objects." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Tensor-parallel training bug and tp-caused OOM are different symptoms and likely different root causes." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "PatchTSMixer post_init policy issue is unrelated to GPT2 attention scaling." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Model loading error vs save_pretrained shard-size question; unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays close to the packet and does not overclaim. The lone accepted soft-edge pair (41669/44246) is conservatively framed as a slowdown/import-time similarity, while the other verdicts are appropriately cautious about differing models, symptoms, or code paths." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 43, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43502", + "issue:43576", + "issue:43618", + "issue:43723", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44222", + "issue:44230", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44387", + "issue:44485", + "issue:44556", + "issue:44655", + "issue:44749", + "issue:44857", + "issue:44938", + "issue:44961", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45125", + "issue:45278", + "issue:45341", + "issue:45375", + "issue:45478", + "issue:45588", + "issue:45600", + "issue:45850" + ], + "soft_pairs": [ + "issue:28282|issue:33453", + "issue:43618|issue:44857", + "issue:43618|issue:44977", + "issue:43618|issue:45588", + "issue:44655|issue:44938", + "issue:43901|issue:44938", + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:43010|issue:44075", + "issue:42890|issue:45341", + "issue:42548|issue:44351", + "issue:44222|issue:45125", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:45125|issue:45478", + "issue:30990|issue:31795", + "issue:45125|issue:45375", + "issue:44387|issue:44556", + "issue:43010|issue:45278", + "issue:30333|issue:33453", + "issue:43723|issue:44556", + "issue:43502|issue:44222", + "issue:43010|issue:44368", + "issue:44315|issue:44360", + "issue:43010|issue:45850", + "issue:43502|issue:44961", + "issue:42831|issue:43874", + "issue:30333|issue:36296", + "issue:44355|issue:45071", + "issue:44355|issue:44655", + "issue:44222|issue:44230", + "issue:43827|issue:44961", + "issue:33453|issue:34689", + "issue:42757|issue:43576" + ], + "prepared_review_unit_hash": "d920bfabba481c67ee8de9ecd9c6162b849002cb89b5c7c51623d5ce7f24c09d", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 37953, + "estimated_input_tokens": 9489, + "estimated_eval_tokens": 19234 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose similarity set around Transformers v5 import/load regressions, but the individual issues are largely different bugs. No pull requests are present. 45278 is the best umbrella issue, though the cluster is too heterogeneous for a strong duplicate canon.", + "confidence": 0.82, + "canonical_issue_reason": "Issue 45278 is the broadest, most representative report: many import errors after upgrading to v5. It best matches the recurring upgrade-related import/load failure theme across the set.", + "canonical_pr_reason": null, + "best_issue_reason": "45278 is the strongest global anchor because it is the most general and recent issue describing the dominant symptom family in this cluster. It is still only a partial fit since many items are unrelated specifics.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "Both are import/loading failures, but one is a missing-PyTorch ImportError and the other is a tokenizer-loading regression; different code paths." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "CLIPOutput attentions assignment and an AMP/CUDA crash in LwDetrImageLoss are unrelated bugs." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "Different symptoms and components: CLIPOutput attentions vs Qwen3.5 flash-attention generation." + }, + { + "left": "issue:43618", + "right": "issue:45588", + "accept": false, + "reason": "AttributeError in flash_attention.py on s_aux=None is a different failure mode from CLIPOutput attentions not being assigned." + }, + { + "left": "issue:44655", + "right": "issue:44938", + "accept": false, + "reason": "Saving Pipeline objects and Python 3.14 import/load failures are not the same underlying bug." + }, + { + "left": "issue:43901", + "right": "issue:44938", + "accept": false, + "reason": "Documentation mismatch for text-classification output is unrelated to Python 3.14 load failures." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "A flaky SAM-HQ integration test is unrelated to model loading for Phi-4 multimodal." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Both involve tests, but one is missing set_seed and the other is a stale device override CI failure; not the same bug." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "Test nondeterminism and broken auto_mappings references are different issues." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "local_files_only behavior and AddedToken keyword duplication are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:44075", + "accept": false, + "reason": "Cache update no_grad decoration and unused SGD args are different code paths." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "A missing set_seed in tests is not the same as a bug in testing_utils.py." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different export regressions." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained behavior and missing tensor-parallel plan are separate problems." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "local_files_only API leakage is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python file errors and a performance regression after upgrade are not the same bug." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both touch Qwen3.5 MoE, but one is tensor-parallel metadata and the other is a from_pretrained regression; too different to merge." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Sentence Transformers getting stuck loading is unrelated to forward-signature documentation confusion." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Missing tensor-parallel plan and a strict-config field drop are different model/config issues." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 memory/OOM behavior and checkpoint reload compatibility are different regressions." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "A no_grad decoration issue is unrelated to a general import-error report." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLFlow reporting on failed training jobs is unrelated to tokenizer loading regression." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer loading in v5 and checkpoint reload after upgrading are both load-related, but not the same concrete failure." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "local_files_only network calls and FP8 save_pretrained bugs are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "Cache update autograd decoration and a tie_word_embeddings warning are different issues." + }, + { + "left": "issue:44315", + "right": "issue:45850", + "accept": false, + "reason": "Liger Kernel not applied with model_init is a specific integration bug, while 45850 is only a vague broad complaint." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file loading errors and PretrainedConfig type-checking regressions are not the same bug." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled Python file errors are unrelated to save_pretrained for pipelines." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "FP8 save_pretrained for MoE and FP8 inference support for Qwen3.5 are related in area but not the same fixable code-path." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs referencing pipeline() after removals and an unrelated placeholder issue are not duplicates." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 model loading breakage are different load failures." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "Importing is_offline_mode and the broken transformers env command are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 44, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:31795", + "issue:33453", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:41669", + "issue:42548", + "issue:42890", + "issue:43010", + "issue:43299", + "issue:43352", + "issue:43408", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44038", + "issue:44246", + "issue:44261", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44373", + "issue:44393", + "issue:44556", + "issue:44623", + "issue:44704", + "issue:44908", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45362", + "issue:45468", + "issue:45542", + "issue:45656", + "issue:45753", + "issue:45850" + ], + "soft_pairs": [ + "issue:43299|issue:44556", + "issue:43010|issue:45656", + "issue:33453|issue:36296", + "issue:43576|issue:43824", + "issue:43576|issue:45071", + "issue:44961|issue:45468", + "issue:31795|issue:38617", + "issue:41628|issue:42548", + "issue:38617|issue:43576", + "issue:43010|issue:43976", + "issue:43576|issue:44351", + "issue:44908|issue:44961", + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "issue:36296|issue:43526", + "issue:44261|issue:44360", + "issue:44273|issue:45003", + "issue:44273|issue:45542", + "issue:44623|issue:45230", + "issue:44393|issue:45753", + "issue:43576|issue:44556", + "issue:44393|issue:45071", + "issue:44038|issue:45125", + "issue:43525|issue:45850", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:44373|issue:44961", + "issue:43572|issue:45850", + "issue:45362|issue:45850", + "issue:42890|issue:44908", + "issue:44704|issue:44908", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:43976|issue:44393", + "issue:43352|issue:44393", + "issue:43576|issue:44908", + "issue:44908|issue:45071", + "issue:44297|issue:45230", + "issue:44295|issue:45230", + "issue:41669|issue:44351" + ], + "prepared_review_unit_hash": "13417d2242fc2cc2d1644ce8c4124387c52c4dd018136473e6178ee13f4a65e7", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 40, + "serialized_chars": 38946, + "estimated_input_tokens": 9737, + "estimated_eval_tokens": 19730 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers issues, with a loose common thread of v5 regressions and import/load breakages. There is no defensible single duplicate target; the closest umbrella is the broad \"v5 breaks many models\" report, but it is too generic to canonicalize the whole set.", + "confidence": 0.18, + "canonical_issue_reason": "No safe canonical: the issues span unrelated bugs (docs, import errors, tokenizer/model loading, training/runtime failures), so they are not the same underlying defect.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the broadest umbrella for the shared v5-breakage theme, but it is too generic to serve as a true duplicate anchor.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Both involve model loading after v5, but one is Qwen3-VL MoE-specific and the other is general checkpoint reload incompatibility." + }, + { + "left": "issue:43010", + "right": "issue:45656", + "accept": false, + "reason": "Different problems: no_grad decoration for cache/layer updates versus DeepSpeed calling optimizer.step twice." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated code paths." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Broken env command is not the same as a missing exported class import." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "v5 env command breakage and PretrainedConfig type-checking regression are different failures." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "No relation beyond being separate model-specific bugs; titles do not indicate the same defect." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion in model.forward is unrelated to an ImportError for layer_type_validation." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different packaging regressions." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "Specific import symbol breakage is not the same as the transformers env command being broken." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache update no_grad issue and Python-version compatibility problem are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:44351", + "accept": false, + "reason": "Env command breakage and HybridCache import failure are different issues." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs handling is unrelated to the racoon-named issue." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Training bug versus documentation mismatch; not the same bug." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "AutoImageProcessor import failure and compiled-file execution errors are different problems." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "Precision/config issue in MLA q_a_layernorm is unrelated to the DSA indexer ReLU discussion." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Both touch lazy/import behavior, but one is a generic lazy-loading complaint and the other is unsafe sys.modules access." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading breakage is not the same as the TensorFlow backend error from tensorboard-only installs." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Processor save_pretrained missing files is concrete; \"Bug report\" is too vague to match it." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Both are Qwen3-VL-related, but one is 2D box hallucination/error and the other is an infinite loop on a specific image." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Broken env command is not the same as checkpoint reload incompatibility after upgrade." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Qwen3-VL output bug and PretrainedConfig type-checking regression are different defects." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Broad Qwen3-VL-Moe failure and missing _tp_plan for tensor parallelism are not the same code-path bug." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config is model-specific, not the broad v5-breakage meta issue." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Removing import * from models and chunked_prefill cache absence are unrelated." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both concern old checkpoints after v5, but they affect different model families and different failure mechanisms." + }, + { + "left": "issue:44373", + "right": "issue:44961", + "accept": false, + "reason": "Wrong position_ids docstring has no connection to the racoon issue." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression is specific, not the broad v5-breakage umbrella." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Qwen3.5 chat crash is a model-specific runtime bug, not the generic v5-wide complaint." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Test flakiness from missing set_seed is unrelated to inverse_sqrt scheduler kwargs handling." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor kwargs forwarding and scheduler kwargs forwarding are different components and bugs." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Import slowness and lazy loading not working are related at a high level but not clearly the same underlying bug." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Model type warning and Liger Kernel not applied with model_init are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python-version compatibility issue is unrelated to the Qwen3-VL bounding-box bug." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention support limitation and Qwen3-VL bounding-box output error are different issues." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Broken env command and scheduler kwargs handling do not share the same bug." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler timescale kwargs and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer config mismatch after save_pretrained is not the same as a generic bug report." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "Buffer/position_ids reading error is a specific bug, while the other item is too vague to match it." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-* cleanup in models and HybridCache import failure are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 45, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:37428", + "issue:38617", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43576", + "issue:43606", + "issue:43673", + "issue:43704", + "issue:43827", + "issue:43874", + "issue:44077", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44315", + "issue:44360", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44655", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45092", + "issue:45230", + "issue:45278", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478", + "issue:45850" + ], + "soft_pairs": [ + "issue:43673|issue:44492", + "issue:41669|issue:45341", + "issue:45278|issue:45850", + "issue:44393|issue:45478", + "issue:43874|issue:45850", + "issue:44315|issue:44829", + "issue:41669|issue:44492", + "issue:43827|issue:44908", + "issue:44077|issue:44861", + "issue:31795|issue:33453", + "issue:41669|issue:44908", + "issue:42371|issue:44492", + "issue:43576|issue:44273", + "issue:44655|issue:44861", + "issue:44360|issue:45468", + "issue:44492|issue:45850", + "issue:44273|issue:44908", + "issue:45230|issue:45310", + "issue:43519|issue:44485", + "issue:41669|issue:43704", + "issue:43519|issue:44908", + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:43704|issue:44485", + "issue:44485|issue:45468", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:43606|issue:45468", + "issue:44261|issue:45468", + "issue:43704|issue:45341", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:43704|issue:44998", + "issue:41669|issue:44998", + "issue:43525|issue:44861", + "issue:43066|issue:44998", + "issue:43572|issue:44861", + "issue:31515|issue:38617", + "issue:44360|issue:44998", + "issue:44230|issue:44623", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:31515|issue:31795", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "244ee41145414b9c3fc768821af05ab88205ec7defb4e8d396d98354aa2e2ecd", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761412, + "estimated_input_tokens": 190353, + "estimated_eval_tokens": 380962 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 51, + "serialized_chars": 42263, + "estimated_input_tokens": 10566, + "estimated_eval_tokens": 21388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is noisy and only loosely connected by Transformers v5 regression reports around loading/import/model-init behavior. I do not see any soft pair that is a true duplicate, so all soft edges are rejected. The best umbrella issue is the broad v5 breakage/import-regression report.", + "confidence": 0.61, + "canonical_issue_reason": "issue:45278 is the best umbrella for the cluster: it is the broadest active report of v5 upgrade breakage and is more representative than the very vague catch-all issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most actionable and central issue among the set, covering the common v5 regression theme better than the narrower model-specific bugs or generic placeholders.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Different bug: chunked_prefill cache handling vs cache-strategy typo." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated: import-star cleanup/perf vs testing_utils bug." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Both are broad v5 complaints, but one is about import errors and the other is a generic breakage report; not the same concrete issue." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Different model/problem: Qwen3-VL bbox output vs Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "Specific GLM46V processor AttributeError vs a generic 'many models break' complaint." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel application via model_init is unrelated to flash_attention_3 training degeneration." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Different issue: import-star cleanup vs cache-strategy typo." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs removal issue vs scheduler kwargs bug." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "Tied-weight key crash is unrelated to the optional post_init policy change." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Docs confusion vs tokenizer-loading regression." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import-star cleanup vs scheduler kwargs bug." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 settings migration vs cache-strategy typo." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Both are v5 regressions, but env CLI breakage and lazy-loading failure are distinct code paths." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving pipelines and tied-weight key handling are unrelated." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "Different models/code paths: DSA ReLU vs Gemma-4 audio positional encoding." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "Cache-strategy typo vs a generic 'many models break' complaint." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading vs inverse_sqrt scheduler kwargs." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report placeholder vs specific Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp math vs GLM-5 RoPE implementation." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star cleanup vs VRAM leak." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Timestamp calculation vs scheduler kwargs." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Docs confusion vs model-loading regression." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Docs confusion vs ImportError in configuration_utils." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger Kernel/model_init issue vs remote-code/meta-init incompatibility." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak vs GLM-5 RoPE implementation." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "Different models and bugs: GLM-5 RoPE vs Gemma-4 audio encoding." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 settings vs VRAM leak." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "local_files_only being ignored is unrelated to timestamp calculation." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Timestamp math vs processor.save_pretrained file output." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Timestamp math vs VRAM leak." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Related tokenizer-v5 theme, but behavior drift and decoder-type bug are different concrete issues." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs bug vs an irrelevant placeholder issue." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight key crash vs apply_chat_template crash." + }, + { + "left": "issue:43704", + "right": "issue:44998", + "accept": false, + "reason": "VRAM leak vs an irrelevant placeholder issue." + }, + { + "left": "issue:41669", + "right": "issue:44998", + "accept": false, + "reason": "Import-star cleanup vs an irrelevant placeholder issue." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "pad_token_id/config regression vs tied-weight key crash." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "pad_token_idx/config regression vs tied-weight key crash." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow checkpoint loading vs missing import symbol." + }, + { + "left": "issue:44360", + "right": "issue:44998", + "accept": false, + "reason": "DSA ReLU issue vs an irrelevant placeholder issue." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "fp8 support request vs processor.save_pretrained file bug." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow run-state reporting vs checkpoint-loading slowdown." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint loading slowdown vs tensor-parallel training bug." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Checkpoint loading slowdown vs docs typo." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "fp8 inference support vs from_pretrained error." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Checkpoint loading slowdown vs tokenizer-loading regression." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return issue vs Gemma-4 audio encoding." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Audio continuous batching support vs fp8 Qwen3.5/Qwen3-VL support." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 3, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "280e1d612c296538eee9e61be0408b96a4c8b34a3f3ed7e2b372b90d5eb322ed", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate feature requests in the same project area, but they target different integrations: Flash Attention 2 support vs GGUF support. They should not be clustered as duplicates or one canonical item.", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue fits both items because they request different capabilities for different architectures/formats, with no shared code-path or concrete overlap.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a duplicate of the other; if forced to pick one representative for its own topic, issue #26350 is the clearer single feature request, but it does not represent the GGUF request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different feature areas and underlying changes: Flash Attention 2 support is an attention backend/architecture feature, while GGUF support is a model-format/loader feature. They are not the same bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 4, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-4", + "nodes": [ + "issue:27088", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "4700850f3349f8e408577c184590c602d100ceffb4c0f56f54a2d8c046c147b8", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4452, + "estimated_input_tokens": 1113, + "estimated_eval_tokens": 2482 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4452, + "estimated_input_tokens": 1113, + "estimated_eval_tokens": 2482 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are all documentation-translation request issues, but they do not look like the same underlying request or bug. The Turkish-specific issue is distinct from the generic language-template issues, and the generic ones lack evidence that they refer to the same language or same translation task.", + "confidence": 0.83, + "canonical_issue_reason": "Issue 27088 is the only concrete, language-specific request ([i18n-TR] Turkish) and is more informative than the generic placeholder-style issues.", + "canonical_pr_reason": null, + "best_issue_reason": "27088 is the best representative of the cluster because it has a specific target language and a fully qualified title, unlike the placeholder issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Different translation requests: Turkish vs an unspecified language-template issue; same broad docs translation theme, but not the same underlying task." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "The titles indicate different language-targeted translation requests; no evidence they are duplicates of one another." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Turkish-specific request versus a generic language placeholder issue; similarity is only in the template text." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "Both are generic template-style issues, but there is no concrete evidence they refer to the same language or same translation effort." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Identical template phrasing alone is not enough to treat them as the same issue; they may represent different languages or separate requests." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "Same placeholder title format, but no explicit target language or shared identifiers to confirm a duplicate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 5, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-15", + "nodes": [ + "issue:36817", + "issue:36879", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:36817|issue:36879", + "issue:36879|issue:41211", + "issue:36879|issue:43909", + "issue:36879|issue:44121", + "issue:36879|issue:43837", + "issue:36879|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:37015|issue:42503", + "issue:36879|issue:37015", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43837|issue:45322", + "issue:43837|issue:43909", + "issue:43909|issue:44205", + "issue:43671|issue:43909", + "issue:44121|issue:45322", + "issue:43837|issue:44121", + "issue:43837|issue:45027", + "issue:37015|issue:45027", + "issue:43837|issue:45177" + ], + "prepared_review_unit_hash": "2d3a7ceb968fc82c3619d90a1f0763914c3e3976e13e728834b5ff1f2a2527f5", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly a set of separate model-request issues (BERT variants, ASR/TTS, OCR, DETR, perception encoders, sparse transformers). They share a generic \u201cadd model support\u201d pattern, but not the same underlying bug or change, so I found no true duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue: the items request different models and capabilities, so they are not duplicate reports of one bug/change.", + "canonical_pr_reason": null, + "best_issue_reason": "No best issue for deduplication: the cluster is too broad and the requests are independent, so none safely represents the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Different model families: EuroBert vs DEIMv2; same broad request style only." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config support vs Qwen3-TTS support; unrelated model types." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert vs RF-DETR are different models and different code paths." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are distinct vision models, not the same request." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR vs LFM2.5 Audio 1.5B target different domains and implementations." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR and circuit-sparsity are unrelated architecture requests." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR (detection) and Qwen3-ASR (speech recognition) are different features." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR and Qwen3-TTS are unrelated model additions." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are different model families and tasks." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT vs circuit-sparsity/circuitgpt are unrelated requests." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT and LFM2.5 Audio 1.5B are not the same underlying change." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are different BERT variants with distinct support needs." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are unrelated model support requests." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture support vs Qwen3-ASR support; different models/tasks." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 and weight-sparse transformer support are separate changes." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 and ModernVBERT are distinct architectures, not duplicates." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 vs Voxtral-4B-TTS-2603 are different model integrations." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are unrelated models and code paths." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT and Qwen3-ASR are different requests." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT and Qwen3-TTS are unrelated model additions." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT and BERT-like models with RoPE overlap only in theme, not in concrete change." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "RoPE-enabled BERT-like models and Voxtral TTS are unrelated." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS and Qwen3-ASR are related branding but different tasks and support work." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio 1.5B are separate audio model requests." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS and weight-sparse transformer support are different underlying changes." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS and Voxtral TTS are different models, not one duplicate issue." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are different speech/audio models." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio 1.5B and SAM3-LiteText are different model families and tasks." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Weight-sparse transformer/circuitgpt and EUPE are unrelated architecture proposals." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR and EUPE are different domains with no shared code-path issue." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR support and weight-sparse transformer support are distinct changes." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral TTS are different speech models/tasks." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT and Voxtral TTS are unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model areas and changes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 6, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-37934-6", + "nodes": [ + "issue:37934", + "issue:42936", + "issue:43240", + "issue:43668", + "issue:43813", + "issue:44031" + ], + "soft_pairs": [ + "issue:37934|issue:43668", + "issue:42936|issue:43240", + "issue:42936|issue:44031", + "issue:42936|issue:43813", + "issue:42936|issue:43668", + "issue:43240|issue:43668", + "issue:43668|issue:44031", + "issue:43668|issue:43813" + ], + "prepared_review_unit_hash": "77ef16526c220b120ad705a68773149b9490ca1c85b97c48a0b194a9fca5d392", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6291, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6291, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are only loosely similar by being small correctness/typo-style reports, but they cover different models, configs, and tokenizer behavior. I do not see any true duplicate pairs in this cluster.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 43668 is the cleanest representative of the loose similarity cluster: a small, concrete config/type-correctness bug. The other issues are separate model, loss, tokenizer, or typo problems rather than the same underlying defect.", + "canonical_pr_reason": null, + "best_issue_reason": "43668 is the most suitable anchor because it is precise and actionable, but it should still be treated as its own issue rather than a duplicate umbrella for the rest.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Different bug classes: Llama4 normalization semantics vs ModernBERT config type hint. No shared code path or concrete duplicate signal." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Mask2Former ignore_value handling and loss-kwargs forwarding are distinct bugs in different code paths." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Segmentation loss parameter usage is unrelated to the tokenizer regex warning regression." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Unrelated issues: model loss parameter usage vs a typo in a quantization attribute name." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Different subsystems and defects: Mask2Former behavior vs a ModernBERT config annotation bug." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss-function kwargs propagation is unrelated to a config type-hint mistake." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "ModernBERT config typing and tokenizer regex warnings are separate, non-overlapping bugs." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "Both are small correctness issues, but one is a config type hint and the other is a string/attribute typo; not the same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 7, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41084-2", + "nodes": [ + "issue:41084", + "issue:43037" + ], + "soft_pairs": [ + "issue:41084|issue:43037" + ], + "prepared_review_unit_hash": "c36a7eacc89892d9fa28a706ce07b0b0b2a36f68a5bdaa7afd47cbfbbb732b84", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are unrelated: one requests block decoding support, the other requests DeepSeek v3.2 support. They should not be clustered as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good canonical representative because they describe different feature requests and do not appear to be the same underlying problem.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Titles and likely intent differ substantially: block decoding vs. DeepSeek v3.2 model support. No evidence they target the same bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 8, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "f0195d356360e4be2cf96a025d3e360b8b81ec2d6d81775a2a3a3b9b9ceaa5f2", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1583, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1583, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related only at a broad theme level (custom trainers/Trainer extensibility), but they describe different problems and code paths: one is about `remove_unused_column`, the other about FLOPs estimation. I would not treat them as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "Issue #43598 is the more specific Trainer customizability problem centered on `remove_unused_column`, making it a clearer canonical representative for that topic.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #43598 is the best single issue to keep because it names a concrete Trainer behavior and likely has the most actionable scope among the two.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "Different underlying issues: `remove_unused_column` behavior vs FLOPs estimation for custom trainers. They share a general Trainer/custom-trainer context but do not look like the same bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 9, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "2285fc9cddcb14291f775cbae5a0e9c9d7f2343015c5eaa2b5b613e46a929b46", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1612, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1612, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are both model-support requests for Qwen variants, but they target different capabilities and different model families: Qwen3-Omni auto-class registration versus Qwen3.5 sequence-classification support. They do not look like the same underlying bug or change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No single issue cleanly represents both items because they request different functionality; if forced, issue 43684 is the broader registration request, but it should not be treated as a duplicate of 44405.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different model families and different requested support: AutoModel/AutoModelForConditionalGeneration registration for Qwen3-Omni versus AutoModelForSequenceClassification support for Qwen3.5. They do not describe the same code path or mergeable fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43835-4", + "nodes": [ + "issue:43835", + "issue:43845", + "issue:43846", + "issue:43859" + ], + "soft_pairs": [ + "issue:43835|issue:43845", + "issue:43835|issue:43846", + "issue:43835|issue:43859", + "issue:43845|issue:43846", + "issue:43845|issue:43859", + "issue:43846|issue:43859" + ], + "prepared_review_unit_hash": "65e5db4f89c74b105667aaf03e8ce93cebc1381a6fb267c0fa92cbe6347c3f08", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4267, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4267, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster looks like low-signal issue noise: three near-identical issues titled \"huggingface \" and one unrelated short title \"Fett\". There isn\u2019t enough substantive content to confidently merge any pair as the same underlying bug.", + "confidence": 0.41, + "canonical_issue_reason": "Issue 43845 is the best representative because it is the earliest of the repeated \"huggingface \" issues and closest to the apparent duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "43845 is the most canonical issue candidate: earliest among the repeated-title issues, with the same minimal wording as 43846 and 43859.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no body or target details to indicate the same bug." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no concrete evidence of a shared underlying problem." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different titles; the available metadata is too thin to treat them as duplicates." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": false, + "reason": "Identical short titles, but there is no substantive description or target evidence to confirm the same issue." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": false, + "reason": "Same generic title text, but the record lacks enough detail to safely merge them as one bug." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": false, + "reason": "Same generic title text, but no body/target evidence establishes a shared underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44371-5", + "nodes": [ + "issue:44371", + "issue:44418", + "issue:44572", + "issue:44573", + "issue:44937" + ], + "soft_pairs": [ + "issue:44371|issue:44572", + "issue:44371|issue:44573", + "issue:44371|issue:44418", + "issue:44371|issue:44937", + "issue:44418|issue:44572", + "issue:44418|issue:44573", + "issue:44572|issue:44573", + "issue:44572|issue:44937", + "issue:44573|issue:44937" + ], + "prepared_review_unit_hash": "6a037fe9c8df00aea33cf06d23992ec1d75af707ac746967ef7fa0185b2ac6e5", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5791, + "estimated_input_tokens": 1448, + "estimated_eval_tokens": 3152 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5791, + "estimated_input_tokens": 1448, + "estimated_eval_tokens": 3152 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All items are low-information spam/placeholder issues with different surface titles and no evidence of a shared underlying bug or change. They should not be merged as duplicates; treat them as separate junk reports, with one generic spam issue as the best representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue:44371 is the earliest clear spam placeholder ('') and is as representative as any other item in this cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44371 is the best representative because it is a generic spam placeholder and predates the other similarly empty items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are generic spam placeholders, but there is no concrete shared bug/change to justify duplicate merging." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Both are generic spam placeholders, but the cluster lacks any actual technical issue identity to unify." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam-like and the other is a documentation suggestion; they do not describe the same underlying problem." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "'' and 'Check out \"Google LLC\"' are different spam-style titles with no evidence of the same issue." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "A documentation enhancement request is unrelated to a spam placeholder issue." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "A documentation enhancement request is unrelated to a spam placeholder issue." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "They are both spam placeholders, but there is no concrete underlying bug/change to establish a true duplicate." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Different spam-like titles with no shared technical subject or code path." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "Different spam-like titles with no shared technical subject or code path." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 12, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45145-2", + "nodes": [ + "issue:45145", + "issue:45151" + ], + "soft_pairs": [ + "issue:45145|issue:45151" + ], + "prepared_review_unit_hash": "30781db1a62da1fafdfeeee6d00a3023179924a5762c35e279add45455063975", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "#45145 and #45151 look like a likely duplicate pair: they have identical titles, very similar body lengths, and a soft-similarity signal. The evidence is suggestive but not definitive, so the duplicate assessment should stay conservative. #45145 is a reasonable canonical choice because it has an inbound reference.", + "confidence": 0.8, + "canonical_issue_reason": "#45145 is a reasonable canonical issue because it has one inbound reference and the pair appears to be a likely duplicate based on identical titles and soft similarity. The packet does not prove the two reports are identical, so this is a conservative choice rather than a definitive identity claim.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the best issue candidate because it is the likelier canonical representative of this duplicate pair and has the only inbound reference. The available evidence supports similarity, but not certainty that the two reports are the same.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": true, + "reason": "Likely duplicate pair: identical titles, very similar body lengths, and a soft-similarity signal. The evidence is enough to treat them as the same underlying report for triage, but not strong enough to claim strict identity." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The conclusion is a bit too strong for the evidence in the packet. The packet supports that #45145 and #45151 have identical titles, similar body lengths, and a soft-similarity signal, but it does not show the bodies themselves or prove they are the same report. The canonical-choice rationale is also only weakly grounded: having one inbound reference makes #45145 a reasonable pick, but not definitively the same duplicate. Please phrase this as a conservative similarity/likely-duplicate assessment rather than a firm identity claim." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45295-2", + "nodes": [ + "issue:45295", + "issue:45373" + ], + "soft_pairs": [], + "prepared_review_unit_hash": "f5fd95fada2f530ab0999e343c17c16266cde0c7182bb22509972ca44827cd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe the same missing Gemma 4 sequence-classification support; the later, more specific open issue is the better cluster representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue #45373 is the clearest canonical tracker: it is open, explicitly names the missing class `Gemma4ForSequenceClassification`, and states the module-level gap relative to Gemma 2/3.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45373 best captures the concrete request and likely remaining work, while #45295 is a shorter earlier duplicate with less detail and is already closed.", + "best_pr_reason": null, + "soft_edge_verdicts": [] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 14, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45672-2", + "nodes": [ + "issue:45672", + "issue:45674" + ], + "soft_pairs": [ + "issue:45672|issue:45674" + ], + "prepared_review_unit_hash": "fe1979d9764c81cd6adcdc76743dcc7300d6132e514bc92e4a2d21f4b821af5e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1669, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1669, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two different 4-bit inference bugs in the same general area, but they do not appear to share the same root cause or fix path. One is a Gemma4/audio-module uint8 `torch.finfo()` TypeError; the other is a BitsAndBytesConfig regression where `llm_int8_skip_modules` drops the default `lm_head` exclusion and triggers an AssertionError.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45674 is the more general and clearly actionable BitsAndBytesConfig regression, with higher discussion activity; if a single representative issue is needed, it is the better anchor, though it is not a duplicate of 45672.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different failure modes and code paths: Gemma4 audio-module dtype handling vs. BitsAndBytesConfig skip-module exclusion logic. Shared 4-bit inference context is too broad to treat as the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 15, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45762-2", + "nodes": [ + "issue:45762", + "issue:45763" + ], + "soft_pairs": [ + "issue:45762|issue:45763" + ], + "prepared_review_unit_hash": "f764d3673d0ebed7502fa72c8dc50f4e42af523ca86355385eefb7930eff99ba", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are not duplicates: they reference different people and different dates, with only a shared surname-like token creating weak similarity.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Different names and birth dates; no evidence they describe the same underlying issue or content." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 16, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "bcec43db9aaf53e57742d54e5153f5efa7382e045bee057d91f46cd0c7d95278", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1481, + "estimated_input_tokens": 371, + "estimated_eval_tokens": 998 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1481, + "estimated_input_tokens": 371, + "estimated_eval_tokens": 998 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both items are closed, empty issues with unrelated person-name/date titles. There is no evidence they describe the same bug or even a software problem; they look like separate low-signal/possibly spam issues.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good canonical representative: both have no body, no links, and no technical content to identify a shared underlying report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "Only superficial similarity in title structure; the names/dates differ and there is no technical content indicating the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-13", + "nodes": [ + "pull_request:39895", + "pull_request:41855", + "pull_request:42668", + "pull_request:43251", + "pull_request:43254", + "pull_request:43424", + "pull_request:43823", + "pull_request:43995", + "pull_request:44827", + "pull_request:45170", + "pull_request:45213", + "pull_request:45655", + "pull_request:45795" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43424", + "pull_request:41855|pull_request:43823", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45655", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:44827", + "pull_request:43995|pull_request:45213", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:45795", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:43823|pull_request:45795", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "0d29c97773f93d624dfca062d790de1cff5692ca75dfb035a9a5b2230e5fd66e", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35204, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35204, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly unrelated PRs. The only true duplicate pair is the two `fixed_cross_entropy` changes (PRs 43251 and 43254), which target the same underlying loss-function fix for issue 43240. Everything else is a different model, docs, or test-only change and should stay separate.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 43240 is the shared underlying bug for the loss-function changes; both 43251 and 43254 are fixing that same `fixed_cross_entropy` kwargs handling.", + "canonical_pr_reason": "PR 43254 is the cleaner canonical representative: it directly adds supported kwargs to `fixed_cross_entropy` with the same code-path fix, while 43251 is a near-identical variant tied to the same issue.", + "best_issue_reason": "If an issue must be chosen for this cluster, 43240 is the only clear canonical issue because it is the explicit target of the duplicate loss-fix PRs.", + "best_pr_reason": "PR 43254 is the best global representative of the duplicate pair because it is the more straightforward implementation of the same `cross_entropy` kwargs support change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Unrelated PRs: VideoPrism model addition vs Executorch dynamic-shape test only." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Different changes: Mistral tokenizer utility methods vs Executorch export test coverage." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Tokenizer method fix is unrelated to adding the MobileLLM model." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor auto-creation robustness work is unrelated to MobileLLM model addition." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Loss-function kwargs fix is unrelated to MobileLLM model implementation." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Different code paths: loss utility kwargs support vs Mistral4 test/model fixes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "Executorch test coverage and Mistral4 fixes are distinct changes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Executorch export tests do not match a new model implementation." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "MobileLLM model addition and config-resolution fix are unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "New MobileLLM model addition is unrelated to Falcon output-interface refactoring." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon refactor and Mistral4 test/model fixes address different models and code paths." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon model refactor is unrelated to the model-creation skill PR." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fixes and layrnorm/layernorm renaming are different bugs/changes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "Mistral4 fixes are unrelated to docs for audio/video processing components." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 test/model fixes are unrelated to config-resolution ordering." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "A model-specific test fix is not the same as the model-creation skill PR." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM model addition and the skill docs/model scaffolding PR are not the same change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45795", + "accept": false, + "reason": "MobileLLM model addition is unrelated to docs for adding audio/video processors." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs implement the same concrete `fixed_cross_entropy` kwargs support fix in the same file and are plausible duplicates for issue 43240." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is well grounded in the packet: the only pair with explicit shared-issue evidence is PRs 43251 and 43254, and they are mergeable as the same `fixed_cross_entropy` kwargs bugfix for issue 43240. The other pairwise judgments stay conservative and are supported by the diff previews (distinct models, docs, or tests)." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40546-2", + "nodes": [ + "pull_request:40546", + "pull_request:42781" + ], + "soft_pairs": [ + "pull_request:40546|pull_request:42781" + ], + "prepared_review_unit_hash": "8fd7a67a7b28d6ef54332d00878a69d875f366a2c18e18cb601f2744337c7603", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs are about VibeVoice, but they are not the same change: #40546 implements the base VibeVoice integration, while #42781 adds a separate realtime variant plus an acoustic tokenizer. Shared auto/model files reflect the same subsystem, not a duplicate code change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "#40546 is the broader, earlier base implementation of VibeVoice and is the more canonical PR for the main model integration; #42781 is a later, narrower realtime follow-up.", + "best_issue_reason": null, + "best_pr_reason": "#40546 is the best PR representative because it covers the core VibeVoice addition end-to-end and is not a draft, whereas #42781 is a draft PR for a distinct realtime extension.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "They share the VibeVoice subsystem and some files, but the PRs target different concrete changes: base VibeVoice integration vs. realtime/acoustic-tokenizer extension. Not a single mergeable duplicate fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 3, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40755-2", + "nodes": [ + "pull_request:40755", + "pull_request:41224" + ], + "soft_pairs": [ + "pull_request:40755|pull_request:41224" + ], + "prepared_review_unit_hash": "441c42788a8270edf914d627337a297c391c773df12b803e0ea8918868b538e4", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4674, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4674, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are unrelated feature additions in different model families and code paths: TimesFM covariate forecasting vs. DINOv3 image classification support. They should not be clustered as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a good canonical representative for a duplicate set because there is no shared underlying bug/change; if forced, the cluster has no valid PR anchor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models, different tasks, and different code paths; one adds TimesFM covariate forecasting while the other adds DINOv3 image classification support." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 4, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41356-2", + "nodes": [ + "pull_request:41356", + "pull_request:44339" + ], + "soft_pairs": [ + "pull_request:41356|pull_request:44339" + ], + "prepared_review_unit_hash": "aead1308c167b0bae6ff11bf9358340baa5e76f816618383418b505a10a9cd01", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two DEIMv2 pull requests target the same model family, but they are not the same change: PR 41356 is an early/basic model + image processor add, while PR 44339 is a much broader follow-up that adds loss code, auto-mappings, conversion tooling, modular files, and more integration work.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44339 is the more complete and representative DEIMv2 implementation; PR 41356 looks like an earlier partial version of the same model bring-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 44339 is the strongest single artifact for the cluster because it subsumes the basic model work and includes the broader integration needed for a full Transformers addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": false, + "reason": "Same model area, but not the same concrete change: 44339 expands the implementation substantially and adds new code paths beyond the basic PR 41356. They look like related iterations, not mergeable duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41797-3", + "nodes": [ + "pull_request:41797", + "pull_request:45186", + "pull_request:45630" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186", + "pull_request:45186|pull_request:45630" + ], + "prepared_review_unit_hash": "089332678d6166adc99f0bdfc8e87ff4486446c1a616fc53a9d03e43ac093365", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10427, + "estimated_input_tokens": 2607, + "estimated_eval_tokens": 5470 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10427, + "estimated_input_tokens": 2607, + "estimated_eval_tokens": 5470 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are separate model-addition efforts (DeepSeek OCR, Isaac, and Kimi2-6), sharing only generic Transformers integration boilerplate. They are not duplicates of the same underlying change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: each pull request adds a different model with distinct files, configs, and implementation details.", + "best_issue_reason": null, + "best_pr_reason": "No single PR is a good representative duplicate target because the PRs do not fix the same code path or implement the same model.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different models and different integrations: DeepSeek OCR vs Isaac. Shared scaffold files are just normal model-registration boilerplate." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Different model additions: Isaac vs Kimi2-6. They touch similar auto-mapping areas but implement unrelated changes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42975-2", + "nodes": [ + "pull_request:42975", + "pull_request:42976" + ], + "soft_pairs": [ + "pull_request:42975|pull_request:42976" + ], + "prepared_review_unit_hash": "8b1299124250ef038da9be352b2f7e3a3c1f8f8666eded607573f7f867568f5b", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs both update GitHub Actions workflow dependencies, but they target different upgrade tracks and different action families. They are related by maintenance theme only, not the same fix/change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #42975 is the better representative because it is the more specific, theme-defining change: upgrading workflow actions for Node 24 compatibility across many workflows.", + "best_issue_reason": null, + "best_pr_reason": "PR #42975 is the best PR candidate overall since it clearly states the compatibility goal and covers the broader set of workflow action version bumps tied to that goal.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Different underlying changes: #42975 upgrades actions like checkout/cache/upload-artifact for Node 24 compatibility, while #42976 upgrades docker/build-push-action and a few other workflow actions to latest versions. They share workflow maintenance context but not the same concrete bug or mergeable change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42978-7", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:43973", + "pull_request:44601", + "pull_request:45490", + "pull_request:45838" + ], + "soft_pairs": [ + "pull_request:42978|pull_request:43448", + "pull_request:42978|pull_request:43451", + "pull_request:42978|pull_request:45490", + "pull_request:43448|pull_request:43451", + "pull_request:43448|pull_request:45490", + "pull_request:43451|pull_request:45490", + "pull_request:43973|pull_request:45838", + "pull_request:44601|pull_request:45838", + "pull_request:45490|pull_request:45838" + ], + "prepared_review_unit_hash": "e58d8ee4363bc81b9732f44f6fee2e8d82d975e9f5cc1413491375fe82da092e", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23511, + "estimated_input_tokens": 5878, + "estimated_eval_tokens": 12012 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23511, + "estimated_input_tokens": 5878, + "estimated_eval_tokens": 12012 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates: they cover separate model additions (ViT NEPA, Molmo, Molmo2, Lfm2 Audio, CTSM, PP-OCRv6) plus one distributed loading feature. Shared files are mostly boilerplate registry/docs updates, not the same underlying change.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No true duplicate PR exists in this cluster. The items are independent feature PRs across different models or subsystems, so none is a canonical duplicate target.", + "best_issue_reason": null, + "best_pr_reason": "PR 45838 is the strongest standalone representative only in the sense that it is a complete model-support PR with concrete implementation and tests. It is still not a duplicate of the others, but it is the most self-contained among the set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different model families (ViT NEPA vs Molmo). Overlap is limited to docs/auto-registration boilerplate, not the same code-path bug or change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different models (ViT NEPA vs Molmo2). Same generic model-addition pattern, but not the same implementation." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "Different models (ViT NEPA vs CTSM). Shared auto/docs edits are incidental." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are distinct model integrations with different filenames and behaviors; not the same underlying change." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo vs CTSM are unrelated model additions." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 vs CTSM are unrelated model additions." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45838", + "accept": false, + "reason": "Lfm2 Audio and PP-OCRv6 text recognition are different modalities and different model implementations." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45838", + "accept": false, + "reason": "One is pipeline-parallel loading support; the other is model support for PP-OCRv6. Different subsystem and different change." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45838", + "accept": false, + "reason": "CTSM and PP-OCRv6 text recognition are different model additions, not mergeable as one fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43291-3", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:44815" + ], + "prepared_review_unit_hash": "05078b5f0ebfd4b7a0f0442028c9256abd073b292d5dcbfea248d21340ff68d5", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7090, + "estimated_input_tokens": 1773, + "estimated_eval_tokens": 3802 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7090, + "estimated_input_tokens": 1773, + "estimated_eval_tokens": 3802 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs do not look like duplicates: one is a Whisper decode/tokenization fix, one is a test-only CLIP/ViT PR with unrelated assertions, and one is a broader FP8 dequantization/loading fix for Mistral. The only similarity is generic \"fix\" wording.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44815 is the most substantial and representative change set in the cluster, with a concrete code-path fix spanning model loading and FP8 dequantization rather than a narrow model-specific tweak or test-only edit.", + "best_issue_reason": null, + "best_pr_reason": "PR 44815 is the strongest candidate to keep as the cluster representative because it contains the clearest, multi-file functional fix and is the least obviously incidental of the three.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Whisper tokenizer decoding vs. CLIP/ViT test assertions; different models, different code paths, and the second PR appears test-only and unrelated." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper decode logic and FP8 dequant/model-loading changes are unrelated bugs in different subsystems; no shared concrete fix path." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "A test-only CLIP/ViT PR does not match a Mistral FP8 dequantization fix; they do not appear to address the same underlying change or bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 9, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-2", + "nodes": [ + "pull_request:43488", + "pull_request:43532" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532" + ], + "prepared_review_unit_hash": "254d39ac4469588b5b02cca2ecc509fb5fc0dc6ee5cab41a2d96b1c13b0ac415", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are not duplicates: #43488 is a small repo-bot/versioning test change, while #43532 is a larger workflow/CI diff-display change. They only share a test filename and do not appear to fix the same underlying code-path problem.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "If one PR must serve as the cluster representative, #43532 is the better canonical choice because it is the broader, more coherent CI/workflow change; #43488 is a separate narrow repo-bot/version bump test PR.", + "best_issue_reason": null, + "best_pr_reason": "#43532 is the stronger representative PR because it has the larger, clearer change set and a more substantive end-to-end purpose than #43488.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Different purposes and code paths: #43488 touches setup/versioning and a ViT test for a repo-bot check, while #43532 rewires CI/comment workflows and related utilities. Shared test filename alone is not enough to treat them as the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43612-2", + "nodes": [ + "pull_request:43612", + "pull_request:43613" + ], + "soft_pairs": [ + "pull_request:43612|pull_request:43613" + ], + "prepared_review_unit_hash": "b685725e55f10d1132e569131698e94f64699464d637259e335f90f00985077c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate feature PRs: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share framework/docs scaffolding, but they target different tasks and model integrations, so they should not be deduplicated.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: 43612 and 43613 are different pipeline features with different task names and model/test coverage, not the same underlying change.", + "best_issue_reason": null, + "best_pr_reason": "If one PR must represent the cluster, 43613 is slightly broader, but it is still a distinct feature from 43612 and should not subsume it.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Different underlying features: concept segmentation vs visual segmentation. Shared scaffolding is expected, but the pipeline code, docs, and model/test targets are not the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43651-2", + "nodes": [ + "pull_request:43651", + "pull_request:43663" + ], + "soft_pairs": [ + "pull_request:43651|pull_request:43663" + ], + "prepared_review_unit_hash": "cdac7247e34a1762717068b04d54689416b99cf4852cc08511e3e5ffe0f00eac", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two separate trainer extensibility PRs in the same file, but they change different behaviors: gradient-accumulation loss scaling vs signature-column filtering. They are not duplicates and should stay separate.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: PR #43651 adds a loss-scaling hook/property, while PR #43663 adds a signature-column helper for a different customization path.", + "best_issue_reason": null, + "best_pr_reason": "PR #43651 is the cleaner representative only in the sense that it is more self-contained, but it does not subsume PR #43663; the PRs solve different problems.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Same file and same subsystem, but different concrete code paths and different extension points: one changes GA loss normalization, the other changes column filtering based on model signatures. They are not mergeable as one duplicate PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 12, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43656-3", + "nodes": [ + "pull_request:43656", + "pull_request:43836", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842", + "pull_request:43836|pull_request:43842" + ], + "prepared_review_unit_hash": "3e068c4c3985878850eef0b92546e20a9811673d8a9e657cb10fee73c9317406", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three open PRs against the same CLI serve module, but only 43836 and 43842 look like alternate fixes for the same TypeAdapter annotation NameError path. PR 43656 appears to address a different annotation/runtime typing issue and is not a true duplicate of the others.", + "confidence": 0.73, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43842 is the most focused fix: it directly addresses the TypeAdapter NameError when pydantic is absent with a minimal TYPE_CHECKING import plus quoted annotation, making it the cleanest representative of this bug.", + "best_issue_reason": null, + "best_pr_reason": "PR 43842 is the best standalone PR candidate because it targets the concrete failure mode most precisely and with the smallest change surface.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "Both touch the same file and mention TypeAdapter, but 43656 looks like a broader typing/annotation cleanup while 43842 specifically fixes the pydantic-missing TypeAdapter import path. They do not read as the same concrete bug fix." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "Both are alternate fixes for the same underlying TypeAdapter NameError in cli/serve.py, using different annotation-handling approaches. They could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays within the packet evidence: 43836 and 43842 both plausibly fix the same TypeAdapter annotation runtime issue in the same file, while 43656 is more broadly about annotation handling and has a different issue target. The soft-edge verdicts are conservative enough, and I do not see an overstatement that would warrant rejection." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43779-2", + "nodes": [ + "pull_request:43779", + "pull_request:43816" + ], + "soft_pairs": [ + "pull_request:43779|pull_request:43816" + ], + "prepared_review_unit_hash": "e7c674adcc031aa8883109a5dfc678b4407fb20b10764302092e384d031ba83a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests appear to implement the same SwanLab integration change: adding run id/resume support in `integration_utils.py` for issue #43698, with one variant also expanding the docs. They are strong duplicate PR candidates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43816 is the cleaner representative: it carries the same SwanLab id/resume support plus the accompanying documentation updates, making it the more complete version of the shared change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43816 is the best global representative because it appears to include the full feature change and docs for SwanLab run id/resume support, while #43779 is the narrower implementation-focused variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43779", + "right": "pull_request:43816", + "accept": true, + "reason": "Same underlying SwanLab callback enhancement for id/resume support in the same file and same issue target; the doc differences do not change the core code-path change, so these are duplicate PRs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both PRs target issue #43698, touch the same file, and the previews indicate the same SwanLab id/resume support with #43816 adding docs. The duplicate/mergeable verdict is conservative enough given the shared target and overlapping code change." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request:44018|pull_request:44068", + "pull_request:44066|pull_request:44071", + "pull_request:44066|pull_request:44068", + "pull_request:44018|pull_request:44066", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request:44116", + "pull_request:44068|pull_request:44722", + "pull_request:44018|pull_request:44116", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44086", + "pull_request:44018|pull_request:44085", + "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request:44059|pull_request:44722", + "pull_request:44098|pull_request:44101", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44073|pull_request:44161", + "pull_request:44059|pull_request:44068", + "pull_request:44056|pull_request:44101", + "pull_request:44018|pull_request:44059", + "pull_request:44101|pull_request:44161", + "pull_request:43997|pull_request:44017", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44018", + "pull_request:43997|pull_request:44161", + "pull_request:44074|pull_request:44161", + "pull_request:44018|pull_request:44161", + "pull_request:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request:44010|pull_request:44073", + "pull_request:44018|pull_request:44129", + "pull_request:43997|pull_request:44074", + "pull_request:43997|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:44071|pull_request:44129", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154" + ], + "prepared_review_unit_hash": "8c4b258c17b89778c8e82cb31b3ca7065e040ec77a28df3f9b44d66b00632b6b", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84902, + "estimated_input_tokens": 21226, + "estimated_eval_tokens": 42708 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75098, + "estimated_input_tokens": 18775, + "estimated_eval_tokens": 37806 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of model-specific refactors toward the same standardized output-tracing pattern, not one true duplicate set. I\u2019d only merge soft edges when the two PRs touch the same model/code path (not just the same meta issue #43979).", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44722 is the best representative of the GPTJ/CodeGen duplicate subset: it covers the shared GPTJ tracing change, also updates CodeGen, and is explicitly tied to #43979.", + "best_issue_reason": null, + "best_pr_reason": "44722 is the broadest clean example of the standardized output-tracing refactor among these PRs, with the clearest same-code-path overlap and the most complete scope.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families/files; same issue target alone does not make these duplicates." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different model families/files; these are separate refactors under the same umbrella issue." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Same GPTJ tracing change in the same file; 44066 looks like the broader sibling/superset." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet and EfficientNet are different model-specific changes." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "Different model families/files; both are output-tracing refactors, but not the same change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "Different model families/files; same refactor theme is not enough." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "Different model families/files; separate model-specific updates." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPTJ/CodeGen vs MGP-STR are unrelated concrete code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Same GPT-Neo file and same output-tracing refactor; these look like duplicate/superset versions." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "Different model families/files; not the same underlying change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPTJ/CodeGen and GPT-Neo are different model-specific changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "Different model families/files; only the meta refactor pattern is shared." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPTJ/CodeGen are unrelated code paths." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "Different model families/files; not the same concrete bug or change." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families/files; same issue target is too broad." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are separate model-specific refactors." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "Different model families/files; no concrete overlap beyond the umbrella refactor." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are different model-specific changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "Different model families/files; same refactor theme is not enough." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are unrelated concrete code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are different model-specific refactors." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "Different model families/files; not the same underlying change." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "Segformer and VisualBert are separate model-specific updates." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different model families/files." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "Different model families/files; same meta issue is not enough." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT2 and MGP-STR are unrelated concrete code paths." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "Different model families/files; not the same bug/change." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT2 and GPTJ/CodeGen are separate model-specific refactors." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and XLM/Flaubert are different model-specific changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are unrelated concrete code paths." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and XLM/Flaubert are separate model-specific refactors." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are different model families/files." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are different model-specific updates." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 are unrelated code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are different model-specific refactors." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet and Segformer are different model families/files." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBert and MPT are unrelated concrete changes." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert and VisualBert are different model-specific refactors." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are separate model-specific changes." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert and XLM/Flaubert are different model families/files." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are unrelated concrete code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are different model-specific refactors." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet and TextNet are separate model-specific changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet and Segformer are different model families/files." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBert and DeBERTa v2 are unrelated concrete code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa v2 and TextNet are different model-specific refactors." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPTJ/CodeGen output-tracing refactor; 44722 appears to be the later consolidated version." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPTJ tracing change in the same file; these could plausibly be merged into one PR." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPTJ and SpeechT5 are different model families/files." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "CVT/FNet and SpeechT5 are unrelated concrete changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa v2 and SpeechT5 are different model-specific refactors." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa v2 and Vits are unrelated code paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall: the packet supports a cluster of related output-tracing refactors rather than one universal duplicate set, and the accepted soft edges are limited to same-file/same-code-path overlaps that look mergeable into one PR. The summary is conservative about the umbrella issue link, and the chosen canonical PR (44722) is well-supported as the best GPTJ/CodeGen representative." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 26, + "review_unit_index": 2, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43997", + "pull_request:44010", + "pull_request:44024", + "pull_request:44056", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44129" + ], + "soft_pairs": [ + "pull_request:44024|pull_request:44076", + "pull_request:44073|pull_request:44074", + "pull_request:44056|pull_request:44073", + "pull_request:44056|pull_request:44074", + "pull_request:43997|pull_request:44010", + "pull_request:44010|pull_request:44129" + ], + "prepared_review_unit_hash": "bace331eb310592fe97c2291a946334fca8b4ccb479dde69ceec4ea7ca1379c4", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84902, + "estimated_input_tokens": 21226, + "estimated_eval_tokens": 42708 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17125, + "estimated_input_tokens": 4282, + "estimated_eval_tokens": 8820 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are model-specific PRs that all modernize output tracing / standardized output capture, but they target different architectures and code paths. They are thematically similar, not duplicates or mergeable into one PR.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44073 is a clear representative of the cluster: it has a concise title, touches the new standardized output-capture pattern directly, and the diff shows the core refactor (`capture_outputs`, `can_return_tuple`, `_can_record_outputs`) in a single model implementation.", + "best_issue_reason": null, + "best_pr_reason": "PR 44073 is the best global exemplar because it most clearly expresses the common pattern across the cluster while remaining narrowly scoped to one model and one output-tracing refactor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Different models (FocalNet vs ImageGPT) and different implementations; same broad refactor theme, but not the same concrete bug or change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "VisualBert and TextNet are unrelated code paths; both adopt standardized output tracing, but these are separate model refactors and not one mergeable change." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet vs VisualBert, with model-specific output-hook wiring; similar pattern, but not the same underlying change." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "MPNet and TextNet changes are independent model migrations to the same infrastructure, not a shared bug fix or duplicate PR." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are different models with separate forward/output refactors; too broad to treat as the same PR." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBert and SpeechT5 target different architectures and output-signature changes; similar tooling migration, but not the same concrete code-path problem." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43998-13", + "nodes": [ + "pull_request:43998", + "pull_request:43999", + "pull_request:44000", + "pull_request:44001", + "pull_request:44002", + "pull_request:44003", + "pull_request:44004", + "pull_request:44025", + "pull_request:44026", + "pull_request:44027", + "pull_request:44028", + "pull_request:44029", + "pull_request:44030" + ], + "soft_pairs": [ + "pull_request:43998|pull_request:44002", + "pull_request:43998|pull_request:44000", + "pull_request:43998|pull_request:44001", + "pull_request:43998|pull_request:44003", + "pull_request:43998|pull_request:44029", + "pull_request:43999|pull_request:44001", + "pull_request:43999|pull_request:44002", + "pull_request:43999|pull_request:44025", + "pull_request:43999|pull_request:44026", + "pull_request:43999|pull_request:44027", + "pull_request:44000|pull_request:44001", + "pull_request:44000|pull_request:44002", + "pull_request:44000|pull_request:44003", + "pull_request:44000|pull_request:44025", + "pull_request:44001|pull_request:44002", + "pull_request:44001|pull_request:44003", + "pull_request:44001|pull_request:44025", + "pull_request:44002|pull_request:44029", + "pull_request:44002|pull_request:44003", + "pull_request:44003|pull_request:44028", + "pull_request:44003|pull_request:44004", + "pull_request:43998|pull_request:44004", + "pull_request:44001|pull_request:44004", + "pull_request:44002|pull_request:44004", + "pull_request:44000|pull_request:44004", + "pull_request:44025|pull_request:44026", + "pull_request:44025|pull_request:44027", + "pull_request:44025|pull_request:44028", + "pull_request:44025|pull_request:44029", + "pull_request:44025|pull_request:44030", + "pull_request:44026|pull_request:44029", + "pull_request:44026|pull_request:44027", + "pull_request:44026|pull_request:44028", + "pull_request:44026|pull_request:44030", + "pull_request:44027|pull_request:44028", + "pull_request:44027|pull_request:44029", + "pull_request:44027|pull_request:44030", + "pull_request:44028|pull_request:44029", + "pull_request:44028|pull_request:44030", + "pull_request:44029|pull_request:44030" + ], + "prepared_review_unit_hash": "76571a9a9def5f8c3b1ce38534c5947b4453a10d72790e97389ab66de19b9a98", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40167, + "estimated_input_tokens": 10042, + "estimated_eval_tokens": 20340 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40167, + "estimated_input_tokens": 10042, + "estimated_eval_tokens": 20340 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is a set of parallel, model-specific refactors to adopt output-tracing / `can_return_tuple` patterns. They share a broad theme but do not appear to be duplicate fixes for the same concrete code path, so all soft edges are rejected.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44003 is the strongest representative of the cluster: it is a substantive output-tracing refactor across two closely related model files and introduces the shared capture/recording machinery, making it the most central example of the pattern.", + "best_issue_reason": null, + "best_pr_reason": "PR 44003 is the best single anchor because it is broader and more infrastructure-like than the one-off model cleanups, while still clearly representing the cluster\u2019s core output-tracing refactor theme.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families (`timm_backbone` vs `upernet`) and different forward/output code paths; same refactor theme, not the same change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "`timm_backbone` and `vision_text_dual_encoder` are unrelated model paths; both refactor output handling but not the same bug or fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Separate model implementations with no shared concrete code path; only a generic output-tracing similarity." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "`timm_backbone` and `mamba/falcon_mamba` use different architectures and forward logic; not mergeable as one PR." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "`timm_backbone` and `rwkv` are unrelated models; shared wording about output tracing is too broad to be a duplicate." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "`mobilenet_v1` and `univnet` are different model code paths with different output objects; not the same underlying fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Different models and different output plumbing; both are refactors, not duplicate fixes." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "`mobilenet_v1` vs `depth_anything` are separate model-specific refactors with no shared concrete defect." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "These touch unrelated encoder/decoder and image backbone code paths; similarity is only at the abstraction level." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Different subsystems and output contracts; not the same underlying change." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "`vision_text_dual_encoder` and `univnet` are unrelated model implementations; same refactor pattern, different changes." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different architecture and output signatures; no evidence they fix the same code-path issue." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "`vision_text_dual_encoder` and `mamba/falcon_mamba` are distinct model families with no shared failing path." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Separate model families and forward methods; only a generic output-tracing overlap." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "`univnet` and `upernet` are unrelated; no shared concrete bug or mergeable combined fix." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model stacks and different output-capture mechanics; not duplicates." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "`univnet` and `depth_anything` are separate model-specific refactors, not the same bugfix." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "`upernet` and `rwkv` are unrelated code paths; same high-level theme only." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "`upernet` and `mamba/falcon_mamba` change different model implementations and cannot plausibly be one PR." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "`mamba/falcon_mamba` and `superpoint` are unrelated models with different output APIs; not the same fix." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "`mamba/falcon_mamba` and `codegen` modify different forward paths and output conventions; not duplicate PRs." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "`timm_backbone` and `codegen` are unrelated model implementations; similarity is only that both touch output handling." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "Different architectures and output contracts; no shared concrete bug/change." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "`upernet` and `codegen` are unrelated subsystems; not mergeable as one PR." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "`vision_text_dual_encoder` and `codegen` have different forward signatures and output paths; too broad to duplicate." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Both are output-tracing refactors, but for different model families (`depth_anything` vs `vision_encoder_decoder`) and different code paths." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "`depth_anything` and `speech_encoder_decoder` are separate model-specific changes, not the same underlying issue." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Different models and different output contracts; only a thematic overlap." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "`depth_anything` and `rwkv` refactor distinct implementations; no shared concrete bug." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "`depth_anything` and `dpr` are different model families with different output plumbing." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "`vision_encoder_decoder` and `rwkv` are unrelated code paths; same refactor theme only." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "Different encoder-decoder stacks and output handling; not the same change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "`vision_encoder_decoder` and `superpoint` are separate model implementations with no shared failure mode." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "Different model families and different forward/output logic; not duplicate PRs." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "`speech_encoder_decoder` and `superpoint` are unrelated; output-tracing similarity is too broad." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "`speech_encoder_decoder` and `rwkv` touch distinct model paths and output semantics." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "Different architectures and output contracts; not the same underlying change." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "`superpoint` and `rwkv` are unrelated models with different forward behavior." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "`superpoint` and `dpr` do not share the same concrete code path or bug." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "`rwkv` and `dpr` are separate model implementations; same general refactor pattern, not a duplicate fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44662-3", + "nodes": [ + "pull_request:44662", + "pull_request:45075", + "pull_request:45401" + ], + "soft_pairs": [ + "pull_request:44662|pull_request:45401", + "pull_request:44662|pull_request:45075", + "pull_request:45075|pull_request:45401" + ], + "prepared_review_unit_hash": "edb556165b2e3c6b50ae9d14866add3f843b53adb72d82b352748caff6c54fb7", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-addition PRs (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share repository plumbing patterns, but they are not the same underlying change and should not be deduplicated.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No true canonical PR for a duplicate cluster here; the PRs implement different models. If one must be picked as the most representative, #45075 is the most anchored because it has an explicit issue target and a fuller, self-contained model integration, but it is still not a duplicate of the others.", + "best_issue_reason": null, + "best_pr_reason": "#45075 is the most complete and structured of the three, with an explicit linked issue and broad integration work, but it should only be treated as a representative PR, not as the same change as the other two.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different models and different code paths: PenguinVL vs Voxtral TTS. Shared auto-registration/docs scaffolding is expected for new model additions, not evidence of the same change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "Different model implementations: PenguinVL vs DeepSeek-OCR-2. They touch similar framework files but introduce unrelated architectures, processors, and tests." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "Different model families and functionality: DeepSeek-OCR-2 vs Voxtral TTS. The overlap is only in generic Transformers integration files, so they are not the same PR-level change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44979-2", + "nodes": [ + "pull_request:44979", + "pull_request:45363" + ], + "soft_pairs": [ + "pull_request:44979|pull_request:45363" + ], + "prepared_review_unit_hash": "a9e8623ca9c99c1c862dbe97653f089d2a1703b53431d09177a71c8d7b128c04", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are related in theme (module/kernel fusion), but they are not the same underlying change: one adds a general Module Fusion API, while the other wires KernelConfig-based n-to-1 fusion into model loading and integrations.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45363 is the broader, end-to-end feature implementation: it touches model loading, integrations, and KernelConfig plumbing, making it the better representative of the cluster than the lower-level API scaffold in #44979.", + "best_issue_reason": null, + "best_pr_reason": "PR #45363 is the most complete and user-facing change in the set; it demonstrates the actual fusion workflow and integrates it across the library, whereas #44979 is mainly a foundational API addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Related area, but different concrete changes and code paths: #44979 introduces a standalone Module Fusion API, while #45363 implements KernelConfig-driven n-to-1 fusion integration. They could not reasonably be merged as one PR without conflating distinct layers of the feature." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 18, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45086-2", + "nodes": [ + "pull_request:45086", + "pull_request:45317" + ], + "soft_pairs": [ + "pull_request:45086|pull_request:45317" + ], + "prepared_review_unit_hash": "b9496540d462586eae3427e382e5059abc9daad5386b2365fba55d580a13cc61", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests address the same AttributeError in `_patch_mistral_regex` by switching from `tokenizer.backend_tokenizer.pre_tokenizer` to `tokenizer.pre_tokenizer` in the same file. PR #45317 is the stronger canonical candidate because it carries the same fix plus test coverage.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45317 is the better canonical PR because it implements the same fix as #45086 and also includes test changes, making it the more complete change set.", + "best_issue_reason": null, + "best_pr_reason": "PR #45317 is the best representative of the cluster: same concrete bug fix, same code path, and it adds validation via tests.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same underlying AttributeError fix in the same function and file; #45317 is a later, test-augmented version of the same change, so they are merge-equivalent enough to treat as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 19, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45115-2", + "nodes": [ + "pull_request:45115", + "pull_request:45569" + ], + "soft_pairs": [ + "pull_request:45115|pull_request:45569" + ], + "prepared_review_unit_hash": "f1b228e661d35cc19ece2db3d53c86ed321d1f963a860b60736bc9108957ef84", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open NemotronH-related PRs overlap on shared model files, but they are not duplicates: one is a refactor/conversion-mapping change, the other is a broader model-family split into dense/sparse variants with docs and tests.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45569 is the better canonical PR because it is the broader, more complete change: it introduces dedicated nemotron_h_dense/nemotron_h_sparse packaging, docs, auto-mapping updates, and tests, whereas #45115 is a narrower refactor focused on inheritance and checkpoint conversion renames.", + "best_issue_reason": null, + "best_pr_reason": "PR #45569 best represents the cluster because it covers the end-state architecture and user-facing model organization for NemotronH, not just internal renaming/refactoring.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Shared NemotronH files do not imply the same change. #45115 is a conversion/architecture refactor toward GraniteMoeHybrid-compatible naming, while #45569 splits NemotronH into dense/sparse model packages and adds docs/tests. They touch related subsystems but are different concrete changes and would not naturally merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 20, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45332-2", + "nodes": [ + "pull_request:45332", + "pull_request:45333" + ], + "soft_pairs": [ + "pull_request:45332|pull_request:45333" + ], + "prepared_review_unit_hash": "fda8a7937bd06ad8b4986e85c21bcebd3da6a62f10d06dfb9e0495bc6dc77001", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related but distinct PRs: #45333 adds per-layer heterogeneous config plumbing, while #45332 builds on that to add broader heterogeneous model/cache/modeling support. They share files and theme, but they do not look like the same concrete change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45333 is the cleaner, more self-contained PR: it introduces the per-layer configuration foundation without the additional modeling/cache changes present in #45332.", + "best_issue_reason": null, + "best_pr_reason": "#45333 is the best representative of the cluster theme because it is the narrower foundational change; #45332 is a later, broader follow-on rather than a duplicate.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Do not merge: #45333 is config-only plumbing, while #45332 adds heterogeneous model/cache behavior and touches multiple runtime code paths. They are related and likely sequential, but not the same fix/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45415-2", + "nodes": [ + "pull_request:45415", + "pull_request:45425" + ], + "soft_pairs": [ + "pull_request:45415|pull_request:45425" + ], + "prepared_review_unit_hash": "97f0812e47929da852c7e9566360b41f17e004479ec927ba5acfdd82e90c97b6", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs are related to typing cleanup, but they address different changes: one is a broad repo-wide type-checking sweep, the other adds specific typing protocols/helpers for core model-loading paths. They are not duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45425 is the more focused and reusable typing-infra change, adding protocol aliases in _typing.py and wiring them into core utilities; PR 45415 is a broader type-checking pass across many files.", + "best_issue_reason": null, + "best_pr_reason": "PR 45425 is the best standalone candidate because it makes a concrete, narrowly scoped typing change with clear code-path impact, whereas PR 45415 is an umbrella type-checking sweep across unrelated modules.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Both are about typing, but they do not fix the same underlying problem. 45415 is a broad type-checking enablement/cleanup PR across many files; 45425 adds specific typing protocols and modeling_utils-related support. They could both land independently." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 22, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45487-4", + "nodes": [ + "pull_request:45487", + "pull_request:45817", + "pull_request:45836", + "pull_request:45843" + ], + "soft_pairs": [ + "pull_request:45487|pull_request:45843", + "pull_request:45487|pull_request:45836", + "pull_request:45817|pull_request:45843", + "pull_request:45836|pull_request:45843" + ], + "prepared_review_unit_hash": "dc05f245832eebd69d40f902f011df55be67eb2f2dcb6ae9e728e410f776af87", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 10388, + "estimated_input_tokens": 2597, + "estimated_eval_tokens": 5450 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 10388, + "estimated_input_tokens": 2597, + "estimated_eval_tokens": 5450 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are separate pull requests fixing different model-parallel issues in different model families; one PR is only a test skip. They are related by theme but not the same underlying change, so no soft merges should be accepted.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45487 is the broadest and most representative concrete code fix in the set: it adjusts device placement for token type ids and updates model-parallel-related module lists across multiple affected models, with corresponding tests.", + "best_issue_reason": null, + "best_pr_reason": "PR 45487 is the best overall representative PR because it contains an actual runtime fix rather than a test-only skip, and its changes are more central to the shared model-parallel failure mode than the narrower model-specific patches.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45843", + "accept": false, + "reason": "Both are model-parallel fixes, but they target different architectures and different root causes: AltCLIP/ChineseCLIP token-id device placement vs. Deimv2 backbone _no_split_modules propagation. Too different to treat as the same change." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45836", + "accept": false, + "reason": "PR 45836 is a test skip for MiniCPM-V/Qwen3.5 cache incompatibility, not a code fix for the same bug as 45487. Different problem and different scope." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45843", + "accept": false, + "reason": "Gemma4 fixes a device-placement/helper and module-splitting issue in Gemma4; Deimv2 propagates _no_split_modules from a backbone. Same broad theme, but not the same concrete bug or mergeable PR." + }, + { + "left": "pull_request:45836", + "right": "pull_request:45843", + "accept": false, + "reason": "Test-only skip for incompatible quantized cache is unrelated to Deimv2 model-parallel module splitting. Not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45548-2", + "nodes": [ + "pull_request:45548", + "pull_request:45662" + ], + "soft_pairs": [ + "pull_request:45548|pull_request:45662" + ], + "prepared_review_unit_hash": "17044c1ce436e4b9fc9034c053ede3e9d160fe33424df392264b9902bc83af7f", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4505, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4505, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs share the EP/transformers area, but they fix different bugs: one is about EP + DeepSpeed ZeRO-3 loading/serialization via accelerate launch, the other about EP + FSDP2 rank-0 broadcast overwriting experts. They are not duplicates and should not be merged into one PR.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:45662 is the better representative because it targets a specific, concrete failure mode with a focused code-path fix (expert parameters being overwritten during shard/broadcast handling).", + "best_issue_reason": null, + "best_pr_reason": "pull_request:45662 is the strongest standalone PR in this cluster: the problem statement is precise, the affected path is clear, and the fix is narrowly aligned to that bug.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Both concern EP/loading, but 45548 fixes config serialization and EP detection for ZeRO-3/accelerate, while 45662 fixes expert parameters being overwritten during FSDP2/broadcast; different underlying bugs and code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 24, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45639-2", + "nodes": [ + "pull_request:45639", + "pull_request:45645" + ], + "soft_pairs": [ + "pull_request:45639|pull_request:45645" + ], + "prepared_review_unit_hash": "2c646fcc1a3c36f0baeb4841a86bcd4832aa9914d85867b7e82ccf5144437d4c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same xdist/captured_info collision problem in Transformers testing utilities. PR #45645 is the more complete fix because it includes the worker-safe file handling plus CI-side aggregation of multiple captured_info files, so it is the better cluster representative.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45645 is the stronger canonical PR because it implements the xdist-safe artifact handling in code and also updates the CI workflow to read all captured_info shards, making it the more complete end-to-end fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45645 best represents the cluster: it fixes the same captured_info/xdist collision path as #45639 but with the fuller solution and supporting workflow changes.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Same underlying bug: xdist workers colliding on captured_info output. #45645 builds on the same helper change and adds the workflow logic needed to consume per-worker files, so these are mergeable into one combined fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 25, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45683-2", + "nodes": [ + "pull_request:45683", + "pull_request:45734" + ], + "soft_pairs": [ + "pull_request:45683|pull_request:45734" + ], + "prepared_review_unit_hash": "eba4ca0f26b2d3be0c00e316270a9341d31af2208b44dbab31b1d3a8e81e7538", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4469, + "estimated_input_tokens": 1118, + "estimated_eval_tokens": 2492 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4469, + "estimated_input_tokens": 1118, + "estimated_eval_tokens": 2492 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs touch the same quantization helper, but they fix different bugs: one special-cases audio submodules, the other changes how default skip lists are combined with user-supplied skips. They should not be clustered as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "45734 is the better representative PR because it fixes the core skip-module composition logic in `get_modules_to_not_convert`, which is broader and more central than the narrow audio-module special case in 45683.", + "best_issue_reason": null, + "best_pr_reason": "45734 is the strongest standalone PR in the set: it addresses a concrete quantization failure mode in the main code path and its fix is directly about the helper\u2019s behavior rather than a model-specific workaround.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45683", + "right": "pull_request:45734", + "accept": false, + "reason": "Both touch quantization skip logic, but 45683 adds audio-tower/embed_audio exclusions while 45734 changes additive handling of `skip_modules`; these are different underlying bugs and would not naturally merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 26, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/manifest.json b/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..bb30c18694270932ae2dcf109b3b7a914e37ef7b --- /dev/null +++ b/snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260509t120021z", + "artifacts": { + "hybrid": "snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-09T12:04:06Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260509T120021Z", + "variant": "hybrid" +} diff --git a/snapshots/20260509T120021Z/manifest.json b/snapshots/20260509T120021Z/manifest.json index fbf7f2c554d71d4b8d320779c0228a8924ba6d22..7c5bcc6685e4d96d9d3861ea85b23bf00ab3065d 100644 --- a/snapshots/20260509T120021Z/manifest.json +++ b/snapshots/20260509T120021Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 129 }, "extracted_at": "2026-05-09T12:00:21Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260509t120021z", + "runs": { + "hybrid-model-20260509t120021z": { + "analysis_id": "hybrid-model-20260509t120021z", + "artifacts": { + "hybrid": "snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260509T120021Z/analysis-runs/hybrid-model-20260509t120021z/manifest.json", + "model": null, + "published_at": "2026-05-09T12:04:06Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260509T120021Z", "watermark": {