diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index f2f5fe93c9f79f0a7cec8a92b0735d5bf2989b33..87285e0116ac990153d6a9562bea72b23420d115 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": "20260517T000046Z", - "generated_at": "2026-05-17T00:04:00Z", + "snapshot_id": "20260517T060024Z", + "generated_at": "2026-05-17T06:03:47Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index 83da9bc6ca90ce798ebef9a0078a2a60ee61d625..b9f0d434ff12459ff094233d96c9d5c914d11802 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": "20260517T000046Z", - "generated_at": "2026-05-17T00:04:00Z", + "snapshot_id": "20260517T060024Z", + "generated_at": "2026-05-17T06:03:47Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -16575,7 +16575,7 @@ { "label": "pull_request", "component_index": 1, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16610,8 +16610,8 @@ "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:43995|pull_request:44827", "pull_request:44827|pull_request:45170", "pull_request:44827|pull_request:45795", "pull_request:44827|pull_request:45655", @@ -16620,7 +16620,7 @@ "pull_request:43823|pull_request:45795", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "b643816093097acffc856c3177dd605121aedaa79e55d93326ce5a4e3ea1a844", + "prepared_review_unit_hash": "91835fef6af75baa179bcbcf202c904c00a740ccda03e139aa67c78d3cce734f", "component_budget": { "node_count": 13, "item_count": 13, @@ -16642,132 +16642,138 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly unrelated PRs that only share loose topical similarity. The only true duplicate-looking pair is the two `loss_utils.py` fixes for `fixed_cross_entropy` targeting issue 43240.", - "confidence": 0.97, + "summary": "This cluster is mostly unrelated PRs that happen to share broad surface areas (models, processors, docs, tests). The only clear duplicate-like pair is the two `fixed_cross_entropy` patches, which both address the same loss helper bug.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the best canonical PR because it is the most explicit and discussed version of the same `fixed_cross_entropy` fix, directly targets issue 43240, and modifies the same code path as 43254. The rest of the items are unrelated model additions, docs, or refactors.", + "canonical_pr_reason": "PR 43251 is the best representative because it makes the concrete `fixed_cross_entropy` fix, explicitly targets issue 43240, and has the stronger discussion signal. PR 43254 is a near-duplicate alternative patch to the same function.", "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the strongest representative of the actual underlying change: a concrete `loss_utils.py` fix for `nn.functional.cross_entropy` with the issue link and fuller review history.", + "best_pr_reason": "PR 43251 is the most canonical PR in the set: it fixes a specific code-path bug, has an explicit issue link, and is more clearly scoped than the other PRs, which are feature additions, docs, or unrelated refactors.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Both are PRs, but one adds VideoPrism and the other adds an executorch dynamic-shape test; they do not fix the same code-path problem." + "reason": "Both are PRs, but one adds a new model and the other adds an Executorch dynamic-shape test; they do not fix the same concrete bug or change." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Mistral tokenizer method additions and a new MobileLLM model are unrelated changes despite both being model work." + "reason": "Tokenizer method additions for Mistral are unrelated to adding the MobileLLM model." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer method additions and executorch dynamic-shape testing are unrelated." + "reason": "A tokenizer API gap fix and an Executorch export test are different changes with no shared underlying defect." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor robustness changes for existing models do not match a new MobileLLM model implementation." + "reason": "Processor auto-loading robustness changes are unrelated to introducing MobileLLM." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "A loss-function bugfix and a new model addition are different underlying changes." + "reason": "Loss helper kwargs support is unrelated to the MobileLLM model addition." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "These touch different areas: cross-entropy loss handling versus Mistral4 test/model fixes." + "reason": "These touch different problems: cross-entropy kwargs vs Mistral4 test/model plumbing." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch export tests and Mistral4 fixes are not the same bug or change." + "reason": "Executorch dynamic-shape testing and Mistral4 fixes are not the same code-path problem." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Executorch export testing and MobileLLM model addition are unrelated." + "reason": "Exportability tests for decoder-only LM are unrelated to the MobileLLM implementation." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "A new model addition and a config-resolution bugfix are different code paths." + "reason": "Adding MobileLLM and fixing config resolution order are separate changes with no shared bug." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "MobileLLM addition and Falcon output-interface refactoring are unrelated." + "reason": "A new model implementation and Falcon output-collection refactoring are unrelated." }, { "left": "pull_request:43995", - "right": "pull_request:44827", + "right": "pull_request:45213", "accept": false, - "reason": "Falcon standardized output refactoring and Mistral4 test fixes do not appear to be the same concrete change." + "reason": "Falcon output-capture refactoring is unrelated to the model-creation skill PR." }, { "left": "pull_request:43995", - "right": "pull_request:45213", + "right": "pull_request:44827", "accept": false, - "reason": "Falcon refactoring and the model-creation skill are unrelated." + "reason": "These are different refactors/fixes in different model families and do not converge on one bug." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test fixes are unrelated to the CLIP-like `layrnorm` rename/conversion cleanup." + "reason": "Mistral4 test fixes and `layrnorm` renaming are unrelated code changes." }, { "left": "pull_request:44827", "right": "pull_request:45795", "accept": false, - "reason": "Mistral4 fixes and documentation for audio/video processors are different changes." + "reason": "A Mistral4 fix and a docs-only audio/video processors PR are not the same underlying change." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 test/model changes are unrelated to the `cls.config` resolution ordering fix." + "reason": "Mistral4 fixes and config-resolution-order changes address different issues." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "A Mistral4 fix and the model-creation skill are clearly not the same underlying change." + "reason": "A model test/fix PR and a meta skill PR are not duplicates and do not share a concrete code-path fix." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "New MobileLLM model code and the model-creation skill are not the same implementation bug or feature." + "reason": "Adding MobileLLM is unrelated to the model-creation skill document update." }, { "left": "pull_request:43823", "right": "pull_request:45795", "accept": false, - "reason": "MobileLLM model addition and docs for audio/video processors only share a broad theme, not a concrete change." + "reason": "MobileLLM model code and docs for audio/video processors are unrelated changes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "Mistral4 test/fix work is unrelated to the docs-only audio/video processors update." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs patch the same `src/transformers/loss/loss_utils.py` `fixed_cross_entropy` function to support extra `cross_entropy` kwargs for the same tracked issue 43240; they are near-identical alternative fixes." + "reason": "Both PRs patch the same `fixed_cross_entropy` helper for the same underlying issue (43240) and are plausible merge alternatives for the same code-path bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative. The only accepted mergeable pair is 43251/43254, which is supported by the shared `loss_utils.py` path and shared issue target 43240. The other pairwise rejections are consistent with the provided filenames, titles, and diff previews, without overstating evidence." + "feedback": "The judgments are grounded in the packet and stay conservative. The duplicate-like pair (43251, 43254) is a plausible same-bugfix alternative in `fixed_cross_entropy`, while the other pairs are reasonably rejected as different model additions, docs, refactors, or tests. The canonical PR choice for 43251 is also supported by the explicit issue link and focused scope." }, "evaluator_used": true, "retried": false, @@ -16778,7 +16784,7 @@ { "label": "pull_request", "component_index": 2, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16794,40 +16800,40 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "e6a788ce47b17309ad4c5d7aa2736b53cbffc8335dce92d1f49fb9dbaabb3a8c", + "prepared_review_unit_hash": "52649b82458f527e64b55521406713ced11a8f4e6a0c1601ed29c920d1758f48", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7224, - "estimated_input_tokens": 1806, - "estimated_eval_tokens": 3868 + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7224, - "estimated_input_tokens": 1806, - "estimated_eval_tokens": 3868 + "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 items are VibeVoice-related PRs, but they are not the same change: #40546 is the main VibeVoice implementation, while #42781 is a separate draft for VibeVoice Realtime plus the acoustic tokenizer. The overlap in auto-mapping/docs comes from shared model-family plumbing, not a single duplicate fix or feature.", - "confidence": 0.82, + "summary": "Two related VibeVoice PRs, but they target different scopes: one adds the base VibeVoice model support, the other adds VibeVoice Realtime plus acoustic-tokenizer/runtime changes. They overlap heavily in files, but they are not the same concrete change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #40546 is the better canonical representative because it is the more complete and reviewed base VibeVoice implementation, with substantial discussion activity and broad model integration.", + "canonical_pr_reason": "PR #40546 is the better canonical representative because it is the original, broader VibeVoice implementation and establishes the main model integration; #42781 is a later, narrower realtime extension built on top of it.", "best_issue_reason": null, - "best_pr_reason": "PR #40546 is the best overall PR in this cluster since it is the main implementation rather than a narrower draft extension, and it has clearer maturity and review signal.", + "best_pr_reason": "PR #40546 is the best overall PR for this cluster since it covers the core VibeVoice addition with the widest surface area and is the natural anchor for the model family.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Reject: they target different underlying work. #40546 implements VibeVoice generally, while #42781 adds VibeVoice Realtime/acoustic-tokenizer pieces. Shared filenames reflect common integration points, not the same concrete bug or mergeable change." + "reason": "Shared VibeVoice integration files, but the PRs are not the same change: #40546 adds the base model, while #42781 adds realtime-specific behavior and acoustic-tokenizer/runtime support. They would not plausibly merge as one PR without conflating distinct features." } ] }, @@ -16841,7 +16847,7 @@ { "label": "pull_request", "component_index": 3, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16857,7 +16863,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "ccbe8030023d9f1f18c4b9541beb8e9b2e1f981eb89963f7883319137cd14920", + "prepared_review_unit_hash": "cba1dac89ea94ae4e92a9716486bf9e7143deb81817bb886f411537891f898d9", "component_budget": { "node_count": 2, "item_count": 2, @@ -16879,18 +16885,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two pull requests are unrelated feature additions in different model families: TimesFM covariates vs. DINOv3 image classification support. They should not be clustered as duplicates.", + "summary": "The two PRs are unrelated feature additions in different model families: TimesFM covariate forecasting vs. DINOv3 image classification support. They should not be clustered as duplicates.", "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 41224 is the more self-contained and specific feature addition, with a clear model-scoped change to DINOv3 image classification support.", + "canonical_pr_reason": "No true canonical PR for this cluster: the PRs target different code paths, different models, and different user-facing features.", "best_issue_reason": null, - "best_pr_reason": "PR 41224 is the better representative for the cluster only in the sense that it is the more concrete, narrowly scoped change; however, the PRs are not duplicates and should remain separate.", + "best_pr_reason": "If one PR must represent the cluster, 41224 is the cleaner standalone feature PR because it has a narrow, well-defined DINOv3 classification support change and more review activity.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different underlying changes and code paths: TimesFM forecasting with covariates versus DINOv3 image classification support. They do not appear mergeable into one PR." + "reason": "Different models and capabilities: TimesFM forecasting with covariates vs. DINOv3 image classification support. They do not fix or add the same underlying change." } ] }, @@ -16904,7 +16910,7 @@ { "label": "pull_request", "component_index": 4, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16967,7 +16973,7 @@ { "label": "pull_request", "component_index": 5, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16985,7 +16991,7 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "13f43cb41ff442cfec3789c7edcf44ec994879fc606ed49569a9bae686e44392", + "prepared_review_unit_hash": "ec40743887501281df6897b815cffc6509f118688384291a643505d9ebb03585", "component_budget": { "node_count": 3, "item_count": 3, @@ -17007,24 +17013,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three items are separate model-addition PRs with overlapping Hugging Face integration boilerplate, but they target different models and code paths (DeepSeek OCR, Isaac, Kimi2-6). No duplicate cluster here; the soft similarities are mostly shared scaffolding.", - "confidence": 0.97, + "summary": "These are three separate model-integration PRs (DeepSeek OCR, Isaac, Kimi2-6) that share boilerplate files but target different models and code paths. They should not be treated as duplicates or merged together.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR #45630 is the most active and substantial representative of the cluster, but it is still a distinct Kimi2-6 integration rather than a duplicate of the others.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different model families and features: DeepSeek OCR vs Isaac. Shared auto/docs/test scaffolding is boilerplate, not the same underlying change." + "reason": "Different integrations for different models (DeepSeek OCR vs Isaac). Shared auto-mapping/docs scaffolding is expected boilerplate, not the same bug or change." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Different model integrations: Isaac vs Kimi2-6. They touch similar HF registration files, but they are separate additions and not mergeable as one fix/change." + "reason": "Different model additions with distinct implementations and files (Isaac vs Kimi2-6). Similar repository plumbing does not mean they fix or add the same concrete code path." } ] }, @@ -17038,7 +17044,7 @@ { "label": "pull_request", "component_index": 6, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17054,12 +17060,12 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "36b24d3a85462c87325137952e25abb7172941b596be816c97979e6db04a4ec8", + "prepared_review_unit_hash": "3fcd693f7d6566343353b54b4caae4aab554b87add91a85badc69441b5e399d0", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5934, + "serialized_chars": 5935, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -17067,7 +17073,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5934, + "serialized_chars": 5935, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -17076,18 +17082,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two distinct workflow-dependency upgrade PRs: one broad GitHub Actions Node 24 compatibility sweep, and one focused docker/build-push-action version bump. They overlap in CI workflows but do not fix the same concrete problem.", - "confidence": 0.92, + "summary": "Both PRs are broad GitHub Actions dependency bumps in workflow files, but they target different action families and different upgrade motives. They are related maintenance changes, not the same concrete change.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #42975 is the better representative because it states the concrete goal (Node 24 compatibility) and covers the broader workflow-action upgrade set.", + "canonical_pr_reason": "No single canonical PR: 42975 updates checkout/cache/upload-artifact for Node 24 compatibility, while 42976 updates docker/build-push-action and other release/build workflow actions.", "best_issue_reason": null, - "best_pr_reason": "PR #42975 is the strongest cluster anchor: broader scope, clearer problem statement, and likely the umbrella workflow-maintenance change compared with the narrower docker-action bump in #42976.", + "best_pr_reason": "42975 is the cleaner representative of the cluster theme because its title and edits focus on a single compatibility-driven Actions upgrade, whereas 42976 is a separate dependency bump set.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Both touch GitHub Actions workflows, but #42975 upgrades core GitHub Actions for Node 24 compatibility while #42976 specifically bumps docker/build-push-action. Different action families and different underlying maintenance goals, so they are not the same change." + "reason": "Different underlying changes: one upgrades core JS GitHub Actions for Node 24 compatibility, the other upgrades docker/build-push-action and related workflow actions. They are not the same bug/change and would not naturally merge into one PR." } ] }, @@ -17101,7 +17107,7 @@ { "label": "pull_request", "component_index": 7, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17130,88 +17136,88 @@ "pull_request:44601|pull_request:45838", "pull_request:45490|pull_request:45838" ], - "prepared_review_unit_hash": "a01225e79e173a8572146fe1492ee070ee6412e2b0429ffe709fc278591d7183", + "prepared_review_unit_hash": "099e1293db05055a827d781b2838e4d010f1e6b40fe5f9d34ccc46fe81dfaff8", "component_budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23538, - "estimated_input_tokens": 5885, - "estimated_eval_tokens": 12026 + "serialized_chars": 23535, + "estimated_input_tokens": 5884, + "estimated_eval_tokens": 12024 }, "budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23538, - "estimated_input_tokens": 5885, - "estimated_eval_tokens": 12026 + "serialized_chars": 23535, + "estimated_input_tokens": 5884, + "estimated_eval_tokens": 12024 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "No duplicates here: the pairwise overlaps are all broad, incidental similarities (docs/auto-registry/test scaffolding) across distinct model-addition PRs or unrelated infra work.", + "summary": "This cluster is mostly a set of unrelated model-addition PRs that only overlap on boilerplate files like docs/toctree and auto mappings. The only infrastructure PR ([Distributed] Add PP support natively) is also unrelated to the model PRs. No soft pair looks like the same underlying change.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR; this cluster is heterogeneous and the PRs add different models or unrelated pipeline-parallel infrastructure rather than the same underlying change.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "No PR is a true duplicate of another. If a representative must be picked, none is suitable because the changes target different models/features and would not merge into one coherent PR.", + "best_pr_reason": "PR 45838 is the strongest standalone PR in the set: it is a complete, self-contained model-support addition with docs, code, and tests. It is not a duplicate of the others, but it is the best representative PR here.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "ViT NEPA and Molmo are different model additions; shared docs/auto-registration files are incidental." + "reason": "ViT NEPA and Molmo are different model families; shared docs/auto-registry edits are boilerplate, not the same change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "ViT NEPA and Molmo2 are distinct model integrations, not the same bug or feature." + "reason": "ViT NEPA vs Molmo2 are separate model additions with different code paths and artifacts." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA and CTSM are separate model additions with no shared code-path change." + "reason": "ViT NEPA and CTSM are unrelated model implementations; overlap is only in shared registry/docs files." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related by name but are different models with different code and docs." + "reason": "Molmo and Molmo2 are related by naming but are distinct models with different implementations and tests." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo and CTSM are unrelated model-support PRs; overlap is only in common registration/docs files." + "reason": "Molmo and CTSM are unrelated model additions; no shared concrete bug or code-path change." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are different model implementations, so they are not duplicates." + "reason": "Molmo2 and CTSM are different model families; similarity is limited to generic registration/docs updates." }, { "left": "pull_request:43973", "right": "pull_request:45838", "accept": false, - "reason": "Lfm2 Audio and PP-OCRv6 text recognition are unrelated model families and would not be one merged PR." + "reason": "Lfm2 Audio is an ASR/audio model add, while PP-OCRv6 is OCR text-recognition support; these are unrelated changes." }, { "left": "pull_request:44601", "right": "pull_request:45838", "accept": false, - "reason": "Pipeline-parallel loading support is infrastructure work, not the same underlying change as PP-OCRv6 model support." + "reason": "Native pipeline-parallel loading support is infrastructure work, not the same concrete model-support change as PP-OCRv6." }, { "left": "pull_request:45490", "right": "pull_request:45838", "accept": false, - "reason": "CTSM and PP-OCRv6 recognition are separate model additions; similarity in docs/auto wiring is superficial." + "reason": "CTSM and PP-OCRv6 are unrelated model additions with different modalities and code paths." } ] }, @@ -17225,7 +17231,7 @@ { "label": "pull_request", "component_index": 8, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17244,52 +17250,52 @@ "pull_request:43291|pull_request:44815", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "8160e7520795c4a578f499f1aaf4b784f1cb31334b59de8043c3075c9e4135f7", + "prepared_review_unit_hash": "a0a21a766c845498d64d13235b7f95e9cb7971a21d40568d9af54881b47d5e02", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7091, - "estimated_input_tokens": 1773, - "estimated_eval_tokens": 3802 + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7091, - "estimated_input_tokens": 1773, - "estimated_eval_tokens": 3802 + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The three PRs are not duplicates: one fixes Whisper tokenization/decode behavior, one is mostly unrelated test edits in CLIP/ViT, and one is an FP8 dequant/loading fix. The apparent similarity is only broad \"modeling/tests\" overlap, not the same bug or change.", - "confidence": 0.96, + "summary": "These PRs are not duplicates of one another. PR 44815 is a substantive dequantization fix across model-loading and FP8 code paths; PR 43291 is a Whisper tokenizer/test change; PR 43665 is test-only and appears unrelated to the other two. None of the soft edges should be accepted as the same underlying change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44815 is the best canonical representative because it contains a concrete code-path fix in FP8/model loading with a clear technical purpose and tests; the other PRs are either a narrow Whisper tokenizer fix or unrelated test-only edits.", + "canonical_pr_reason": "PR 44815 is the strongest representative of the cluster because it is the only substantial production-code bugfix; the other PRs are narrow or test-only and cover different code paths.", "best_issue_reason": null, - "best_pr_reason": "PR 44815 is the strongest standalone PR in this cluster: it addresses a specific dequantization/loading bug and is materially different from the other two, which do not fix the same underlying problem.", + "best_pr_reason": "PR 44815 is the best single PR to keep as the cluster anchor because it has the clearest concrete fix and the broadest, most coherent implementation scope.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Different subsystems and different problems: Whisper tokenizer decode logic versus CLIP/ViT test edits. No shared bug or mergeable unified fix." + "reason": "Whisper tokenizer/test changes and CLIP/ViT test edits are unrelated code paths; they do not fix the same bug and would not plausibly be one PR." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper decode/tokenization changes are unrelated to FP8 dequant/loading logic. They do not fix the same code-path problem." + "reason": "One PR is Whisper decode/test cleanup, the other is FP8 dequant/model-loading work; different subsystems and different underlying problems." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "Test-only CLIP/ViT edits are unrelated to the FP8 dequant/model-loading bug. Similarity is superficial only." + "reason": "Test-only CLIP/ViT edits do not share a concrete bug or implementation path with the FP8 dequantization fix, so they should not be merged as duplicates." } ] }, @@ -17303,7 +17309,7 @@ { "label": "pull_request", "component_index": 9, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17319,12 +17325,12 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "e962f9eff9a941a923954c14915709f7d1186dc6e8999b207af49f9dc5fa455b", + "prepared_review_unit_hash": "2dc2fd1a8079f505583325195722473cb110b253e4f7a4d33cc2f6325d265e68", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4563, + "serialized_chars": 4562, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17332,7 +17338,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4563, + "serialized_chars": 4562, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17341,18 +17347,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two pull requests are not duplicates: one is a small repo-bot/version-format test PR, while the other changes CI/workflow and testing infrastructure. The only overlap is an incidental shared test file, not the same underlying fix.", - "confidence": 0.95, + "summary": "These two PRs are not duplicates: one is a synthetic setup/version/repo-bot check change, while the other is a broader CI/workflow and test-infra diff. The only overlap is a shared Vit test file, which is not enough to indicate the same underlying fix.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43532 is the better representative of the cluster because it contains the larger, more substantive code change set and broader context; PR #43488 is a narrow test/bot-check change.", + "canonical_pr_reason": "No clear canonical PR: 43488 is a narrow repo-bot/setup version test, while 43532 is a broader CI/workflow and testing-utils change; they do not represent the same change.", "best_issue_reason": null, - "best_pr_reason": "PR #43532 is the best overall representative since it touches the main operational area in the cluster (workflows/testing) and is more informative than the tiny placeholder PR #43488.", + "best_pr_reason": "43532 is the better representative PR only in the sense that it is the more substantial, multi-file change, but it is still not a duplicate of 43488.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Reject: these PRs address different problems. #43488 changes setup/versioning for a bot-format check and adds a dependency; #43532 edits CI/workflow logic plus testing utilities. Shared test-file touches are incidental, not the same concrete code-path fix." + "reason": "Shared Vit test file aside, the diffs target different problems: 43488 adjusts setup/versioning for a bot check, while 43532 changes workflow and testing infrastructure. They are not the same code-path fix and would not be merged as one PR." } ] }, @@ -17366,7 +17372,7 @@ { "label": "pull_request", "component_index": 10, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17382,12 +17388,12 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "682932f5b20129ec4f87f24de89fa6189208d9aecb1d4dccac85ffb5f4c588e7", + "prepared_review_unit_hash": "e97d0845a9a11bbc950cfad8561ac8373c344bea4a0df2c63302453cde1103df", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6081, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17395,7 +17401,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6081, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17404,18 +17410,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related but distinct PRs: one adds a promptable concept segmentation pipeline, the other adds a promptable visual segmentation pipeline. They share documentation/pipeline scaffolding, but they target different task definitions, code paths, and model integrations, so they should not be merged as duplicates.", - "confidence": 0.98, + "summary": "These are related but distinct feature PRs: one adds Promptable Concept Segmentation, the other adds Promptable Visual Segmentation. They share boilerplate/docs/pipeline-registry changes, but they target different pipelines and model integrations, so they should not be treated as duplicates.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No canonical PR: the two pull requests implement different segmentation pipelines with different model support and task docs.", "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the more comprehensive segmentation-pipeline change, with broader backend and test coverage, but it still addresses a different feature than 43612.", + "best_pr_reason": "PR 43613 is the broader of the two and touches more model integrations, but it is still a separate feature from 43612, not a duplicate.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Different features: concept segmentation vs visual segmentation. Similar scaffolding and filenames, but distinct pipeline implementations, docs, and model/test surfaces; not the same underlying change." + "reason": "Different concrete changes: promptable concept segmentation vs promptable visual segmentation. Shared scaffolding and docs do not make them the same underlying fix or change." } ] }, @@ -17429,7 +17435,7 @@ { "label": "pull_request", "component_index": 11, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17445,7 +17451,7 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "8b5513d76a70f529b4dbe7b33d06f02cafb5a3e151d8c924be1be0f49e98685c", + "prepared_review_unit_hash": "87092bbea97112da3a4ba67afe6c3cab436364d77999ed5fe212710f17f4f72b", "component_budget": { "node_count": 2, "item_count": 2, @@ -17467,18 +17473,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs both touch `trainer.py` but implement unrelated trainer extensibility changes: one adjusts gradient-accumulation loss scaling, the other refactors signature-column filtering for custom trainers/PEFT. They are not duplicates.", + "summary": "Both pull requests modify `src/transformers/trainer.py`, but they address different trainer extension points: one changes gradient-accumulation loss scaling, the other refactors signature/column filtering for PEFT models. Shared filename alone is not enough to treat them as the same change.", "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: the cluster contains two different enhancements in separate code paths, not one underlying change.", + "canonical_pr_reason": "PR 43651 is the better representative anchor because it introduces a clear, self-contained trainer behavior hook (`_loss_is_scaled_for_ga`) and changes the training-step loss scaling path; however, it is not a duplicate of 43663.", "best_issue_reason": null, - "best_pr_reason": "No single best PR is a good global representative here because the PRs solve different problems (loss scaling vs. column filtering).", + "best_pr_reason": "PR 43651 is the stronger standalone PR for the cluster only by being the more explicit behavior change. PR 43663 is a separate override hook for signature-column filtering and should not be merged with 43651 as the same fix.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different concrete behaviors and code paths in `trainer.py`; one changes gradient accumulation loss normalization, the other adds an overridable helper for input column filtering. They are not plausibly one merged PR." + "reason": "Different concrete code paths and extension goals: gradient-accumulation loss scaling vs. signature column filtering for PEFT/custom trainers. They share a file, not a bug or change." } ] }, @@ -17492,7 +17498,7 @@ { "label": "pull_request", "component_index": 12, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17510,7 +17516,7 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "c54f6889aeb77da1acfab74dc8b30951746c5a535fb16ba034870ba881ad167a", + "prepared_review_unit_hash": "c45245388f8300ce91a42ac5e2fb737d0c2943283e5b7101e62e6e8c7386bfe3", "component_budget": { "node_count": 3, "item_count": 3, @@ -17532,30 +17538,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Three open PRs touch `src/transformers/cli/serve.py` around `TypeAdapter`/annotation runtime issues. `43842` is the cleanest representative; `43836` looks like an alternate fix for the same `TypeAdapter` NameError; `43656` appears adjacent but not clearly the same change.", - "confidence": 0.68, + "summary": "Two PRs (43836 and 43842) are near-duplicates for the same TypeAdapter runtime-import NameError in `src/transformers/cli/serve.py`; 43656 looks related but is broader and less clearly the same concrete fix.", + "confidence": 0.74, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43842 is the most direct and focused fix for the shared CLI `TypeAdapter` NameError: it keeps `TypeAdapter` out of runtime imports via `TYPE_CHECKING` and quotes the annotation, matching the bug description cleanly.", + "canonical_pr_reason": "PR 43842 is the cleanest, most targeted fix for the `TypeAdapter` NameError: it explicitly guards the `pydantic` import with `TYPE_CHECKING` and quotes the annotation, directly addressing the runtime import problem with minimal scope.", "best_issue_reason": null, - "best_pr_reason": "43842 is the best overall representative of the cluster because it most clearly and narrowly addresses the concrete runtime failure in the serve CLI without broader unrelated type-hint churn.", + "best_pr_reason": "PR 43842 is the best representative of the cluster because it most directly and narrowly fixes the runtime `TypeAdapter` annotation issue in the CLI serve code path.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Same file and similar symptom, but the shown edits point to a different annotation cleanup and a different issue target; not enough evidence that this is the same concrete bug/change as 43842." + "reason": "Both mention `TypeAdapter` in `cli/serve.py`, but 43656 appears to be a broader typing cleanup with additional annotation changes and a different issue target; the evidence is not strong enough that they fix the exact same concrete bug." }, { "left": "pull_request:43836", "right": "pull_request:43842", "accept": true, - "reason": "Both PRs target the same explicit issue and the same serve.py `TypeAdapter` NameError; they are alternate implementations of the same underlying bug fix and plausibly one merged change." + "reason": "These are alternative implementations of the same fix for the same runtime `TypeAdapter` NameError in `src/transformers/cli/serve.py`, and both target the same issue, so they look duplicate-equivalent." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: 43842 is the smallest, most targeted TypeAdapter fix in `serve.py`; 43836 is broader but still on the same issue target; and 43656 is adjacent annotation cleanup with a different issue target. The soft-edge verdicts are conservative enough, especially the rejection of 43656 vs 43842." + "feedback": "The summary is grounded in the packet: 43836 and 43842 share the same explicit issue target (43824) and both modify the same file to address the TypeAdapter import/annotation runtime problem, while 43656 has a different issue target (43576) and only soft similarity. The soft-edge verdicts are conservative enough." }, "evaluator_used": true, "retried": false, @@ -17566,7 +17572,7 @@ { "label": "pull_request", "component_index": 13, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17632,7 +17638,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 2, "status": "reviewed", @@ -17744,12 +17750,12 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "772a703a2edc6d6bf3973ecb8c7c0874f7896767256cc6d61f29242321f605c7", + "prepared_review_unit_hash": "7c39461dba1b542d6d2703a92e226bd07805ef58d023d6718ebe19da8a4d5301", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84897, + "serialized_chars": 84899, "estimated_input_tokens": 21225, "estimated_eval_tokens": 42706 }, @@ -17757,7 +17763,7 @@ "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75094, + "serialized_chars": 75093, "estimated_input_tokens": 18774, "estimated_eval_tokens": 37804 }, @@ -17766,378 +17772,360 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is not one homogeneous duplicate cluster; it is a family of model-specific output-tracing refactors, many linked to issue #43979. Most cross-model pairs should be rejected; only same-model GPT-J and GPT-Neo PR pairs look like true duplicates or near-duplicates.", - "confidence": 0.84, - "canonical_issue_reason": "Issue #43979 is the umbrella tracker for the standardized output-tracing refactor that most of these PRs explicitly reference.", - "canonical_pr_reason": "PR #44722 is the strongest representative of the GPT-J/CodeGen branch: it explicitly targets #43979 and shows the concrete decorator-based tracing refactor on the same code paths.", - "best_issue_reason": "#43979 is the best global anchor because it scopes the shared refactor theme across many model-specific PRs.", - "best_pr_reason": "#44722 is the best single PR representative because it is explicit, concrete, and broad enough to illustrate the standardized tracing change without being just a narrow cleanup.", + "summary": "This cluster is mostly a set of model-specific refactors around standardized output tracing, but most pairs are not true duplicates because they touch different model families and code paths. The only clear duplicate groups are the GPT-J/CodeGen refactors and the GPT-Neo refactors.", + "confidence": 0.83, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44066 is the best representative: it has an explicit issue link, covers the core GPT-J/CodeGen output-tracing refactor, and is the broadest coherent version of that same concrete change.", + "best_issue_reason": null, + "best_pr_reason": "PR 44066 is the strongest global representative for this cluster because it centers the shared GPT-J/CodeGen output-tracing change with issue linkage, while most other items are narrower or on unrelated models.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different models and code paths; same tracking theme is not enough." + "reason": "Different model families and code paths (FNet/CVT vs GPT-J); only the output-tracing theme overlaps." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "CVT/FNet vs DeBERTa V2 are unrelated model implementations." + "reason": "Different model families and code paths; not the same bug or change." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both are GPT-J output-tracing refactors on the same code path and could plausibly be merged." + "reason": "Same GPT-J output-tracing refactor on the same code path; one PR could plausibly absorb the other." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "RegNet/ResNet refactors are separate model-specific changes." + "reason": "Different CNN model implementations and refactor scopes; same broad theme only." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet and GPT-J/CodeGen are different code paths." + "reason": "EfficientNet vs GPT-J/CodeGen are unrelated code paths." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen vs EfficientNet; same issue family only at a high level." + "reason": "GPT-J/CodeGen and EfficientNet are unrelated concrete changes." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa V2 are distinct model paths." + "reason": "MobileNetV2 and DeBERTa are unrelated model paths." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen output tracing is unrelated to MGP-STR." + "reason": "GPT-J/CodeGen refactor vs MGP-STR refactor; different models and implementations." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen and MPT are separate model refactors." + "reason": "GPT-J/CodeGen and MPT are unrelated code paths." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Same GPT-Neo output-tracing refactor on the same model code path." + "reason": "Same GPT-Neo output-tracing refactor on the same model file; these look like duplicate/iterative versions of one change." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are different model implementations." + "reason": "GPT-J/CodeGen vs GPT-Neo; same topic, different concrete model code." }, { "left": "pull_request:44018", - "right": "pull_request:44044", + "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and DeBERTa V2 are not the same underlying change." + "reason": "GPT-Neo and RegNet are different model families and changes." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet output tracing and GPT-J/CodeGen output tracing are unrelated model-specific changes." + "reason": "RegNet vs GPT-J/CodeGen; unrelated code paths." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are different code paths." + "reason": "MGP-STR and GPT-J are unrelated implementations." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet vs GPT-J; same theme but not the same change." + "reason": "RegNet vs GPT-J; not the same concrete refactor." }, { "left": "pull_request:44018", - "right": "pull_request:44019", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and ResNet are separate model refactors." + "reason": "GPT-Neo vs MPT are different model code paths." }, { - "left": "pull_request:44019", - "right": "pull_request:44071", + "left": "pull_request:44071", + "right": "pull_request:44086", "accept": false, - "reason": "ResNet and MPT are distinct implementations." + "reason": "MPT and MGP-STR are unrelated changes." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different model code paths." + "reason": "GPT-Neo vs GPT-J/CodeGen; same broad theme but different model code." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert are unrelated model-specific refactors." + "reason": "GPT-Neo vs Flaubert are unrelated model implementations." }, { "left": "pull_request:44071", - "right": "pull_request:44722", - "accept": false, - "reason": "MPT and GPT-J/CodeGen are different code paths." - }, - { - "left": "pull_request:44018", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert/XLM are separate model implementations." + "reason": "MPT vs Flaubert/XLM are unrelated code paths." }, { "left": "pull_request:44018", - "right": "pull_request:44085", + "right": "pull_request:44059", "accept": false, - "reason": "GPT-Neo and GPT-J are different models." + "reason": "GPT-Neo vs GPT-2 are different model-specific refactors." }, { - "left": "pull_request:44018", + "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated code paths." + "reason": "GPT-J vs MGP-STR; unrelated models and code paths." }, { - "left": "pull_request:44071", - "right": "pull_request:44085", + "left": "pull_request:44098", + "right": "pull_request:44101", "accept": false, - "reason": "MPT and GPT-J are distinct model refactors." + "reason": "ViLT and Flaubert/XLM are different model families." }, { - "left": "pull_request:44071", - "right": "pull_request:44086", + "left": "pull_request:44019", + "right": "pull_request:44071", "accept": false, - "reason": "MPT and MGP-STR are not the same underlying bug/change." + "reason": "RegNet vs MPT; unrelated concrete changes." }, { - "left": "pull_request:43997", - "right": "pull_request:44073", + "left": "pull_request:44018", + "right": "pull_request:44086", "accept": false, - "reason": "RegNet and VisualBert are different model code paths." + "reason": "GPT-Neo vs MGP-STR; different code paths." }, { - "left": "pull_request:44017", - "right": "pull_request:44071", + "left": "pull_request:44018", + "right": "pull_request:44059", "accept": false, - "reason": "Segformer and MPT are unrelated refactors." + "reason": "GPT-Neo and GPT-2 are separate model implementations." }, { - "left": "pull_request:44017", - "right": "pull_request:44073", + "left": "pull_request:44071", + "right": "pull_request:44076", "accept": false, - "reason": "Segformer and VisualBert are separate model-specific changes." + "reason": "MPT vs ImageGPT; unrelated model code." }, { "left": "pull_request:44068", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and MPT are different model implementations." + "reason": "GPT-Neo vs MPT; different code paths." }, { "left": "pull_request:44071", - "right": "pull_request:44076", + "right": "pull_request:44086", "accept": false, - "reason": "MPT and ImageGPT are different code paths." + "reason": "MPT vs MGP-STR; unrelated changes." }, { - "left": "pull_request:44074", - "right": "pull_request:44101", + "left": "pull_request:44059", + "right": "pull_request:44068", "accept": false, - "reason": "TextNet and Flaubert/XLM are unrelated model refactors." + "reason": "GPT-2 vs GPT-Neo are different model-specific refactors." }, { - "left": "pull_request:44056", - "right": "pull_request:44161", + "left": "pull_request:44017", + "right": "pull_request:44722", "accept": false, - "reason": "MPNet and LongT5 are different model code paths." + "reason": "Segformer vs GPT-J/CodeGen; not the same bug or change." }, { - "left": "pull_request:43997", - "right": "pull_request:44018", + "left": "pull_request:44017", + "right": "pull_request:44161", "accept": false, - "reason": "RegNet and GPT-Neo are separate model-specific changes." + "reason": "Segformer and LongT5 are unrelated model code paths." }, { - "left": "pull_request:43997", + "left": "pull_request:44073", "right": "pull_request:44161", "accept": false, - "reason": "RegNet and LongT5 are unrelated refactors." + "reason": "VisualBert vs LongT5; different implementations." }, { - "left": "pull_request:44074", - "right": "pull_request:44161", + "left": "pull_request:44059", + "right": "pull_request:44071", "accept": false, - "reason": "TextNet and LongT5 are different code paths." + "reason": "GPT-2 and MPT are unrelated model refactors." }, { - "left": "pull_request:44018", - "right": "pull_request:44161", + "left": "pull_request:44056", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and LongT5 are different model implementations." + "reason": "MPNet vs MPT; different code paths." }, { "left": "pull_request:43997", - "right": "pull_request:44071", + "right": "pull_request:44017", "accept": false, - "reason": "RegNet and MPT are separate model refactors." + "reason": "RegNet vs Segformer are different models." }, { "left": "pull_request:44010", "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBert and MPT are not the same underlying change." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44129", - "accept": false, - "reason": "GPT-Neo and SpeechT5 are different model code paths." + "reason": "SqueezeBert and MPT are unrelated changes." }, { "left": "pull_request:44010", "right": "pull_request:44073", "accept": false, - "reason": "SqueezeBert and VisualBert are unrelated model-specific changes." - }, - { - "left": "pull_request:44017", - "right": "pull_request:44722", - "accept": false, - "reason": "Segformer and GPT-J/CodeGen are different models." + "reason": "SqueezeBert vs VisualBert; different model code." }, { "left": "pull_request:44017", - "right": "pull_request:44161", + "right": "pull_request:44074", "accept": false, - "reason": "Segformer and LongT5 are separate code paths." + "reason": "Segformer and TextNet are unrelated model-specific refactors." }, { "left": "pull_request:44073", "right": "pull_request:44101", "accept": false, - "reason": "VisualBert and Flaubert/XLM are distinct model implementations." + "reason": "VisualBert and Flaubert/XLM are different code paths." }, { "left": "pull_request:44059", - "right": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 vs MGP-STR; unrelated model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", "accept": false, - "reason": "GPT-2 and MPT are different code paths." + "reason": "GPT-Neo and SpeechT5 are unrelated changes." }, { "left": "pull_request:44056", - "right": "pull_request:44101", + "right": "pull_request:44161", "accept": false, - "reason": "MPNet and Flaubert/XLM are unrelated refactors." + "reason": "MPNet vs LongT5; different model code paths." }, { "left": "pull_request:43997", - "right": "pull_request:44056", + "right": "pull_request:44074", "accept": false, - "reason": "RegNet and MPNet are different model-specific changes." + "reason": "RegNet and TextNet are unrelated model families." }, { - "left": "pull_request:43997", - "right": "pull_request:44018", + "left": "pull_request:44056", + "right": "pull_request:44068", "accept": false, - "reason": "RegNet and GPT-Neo are different code paths." + "reason": "MPNet vs GPT-Neo; same theme, different concrete change." }, { "left": "pull_request:44071", "right": "pull_request:44076", "accept": false, - "reason": "MPT and ImageGPT are unrelated model implementations." + "reason": "MPT vs ImageGPT; unrelated implementations." }, { "left": "pull_request:44074", - "right": "pull_request:44101", - "accept": false, - "reason": "TextNet and Flaubert/XLM are not the same underlying change." - }, - { - "left": "pull_request:44056", - "right": "pull_request:44161", + "right": "pull_request:44129", "accept": false, - "reason": "MPNet and LongT5 are different model refactors." + "reason": "TextNet and SpeechT5 are different model paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44018", + "left": "pull_request:44018", + "right": "pull_request:44085", "accept": false, - "reason": "RegNet and GPT-Neo are separate model code paths." + "reason": "GPT-Neo vs GPT-J; not the same model-specific refactor." }, { "left": "pull_request:44010", "right": "pull_request:44044", "accept": false, - "reason": "SqueezeBert and DeBERTa V2 are different model implementations." + "reason": "SqueezeBert and DeBERTa are unrelated code paths." }, { "left": "pull_request:44044", "right": "pull_request:44074", "accept": false, - "reason": "DeBERTa V2 and TextNet are unrelated refactors." + "reason": "DeBERTa vs TextNet; different model families." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Same GPT-J/CodeGen decorator-based output tracing change on overlapping code paths." + "reason": "Same GPT-J/CodeGen standardized output-tracing refactor on the same code path; these are mergeable duplicates." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Both target the GPT-J output-tracing refactor and are close enough to combine." + "reason": "Both are GPT-J output-tracing refactors on the same file; one is a narrower version of the same change." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J and SpeechT5 are different model code paths." + "reason": "GPT-J vs SpeechT5 are unrelated model implementations." }, { "left": "pull_request:43996", "right": "pull_request:44007", "accept": false, - "reason": "CVT/FNet and RegNet/ResNet are not the same underlying change." + "reason": "FNet/CVT vs RegNet/ResNet/RT-DETR; different concrete changes." }, { "left": "pull_request:43996", "right": "pull_request:44129", "accept": false, - "reason": "CVT/FNet and SpeechT5 are unrelated model-specific refactors." + "reason": "FNet/CVT and SpeechT5 are unrelated model code paths." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa V2 and SpeechT5 are different code paths." + "reason": "DeBERTa vs SpeechT5; not the same bug or change." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa V2 and VITS are separate model implementations." + "reason": "DeBERTa and VITS are unrelated model implementations." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: #43979 is clearly the umbrella issue for many of these model-specific output-tracing refactors, and #44722 is a reasonable representative PR because it explicitly targets #43979 and covers the GPT-J/CodeGen code paths. The soft-edge verdicts are conservative overall: cross-model pairs are rejected, and the accepted pairs stay within closely related same-family changes that look mergeable into a single bugfix PR." + "feedback": "The summary is grounded in the packet and stays conservative. The rejected soft-edge pairs are mostly clearly cross-model or cross-family, and the accepted pairs are the only ones that plausibly look like the same mergeable bugfix (GPT-J/CodeGen and GPT-Neo refactors)." }, "evaluator_used": true, "retried": false, @@ -18148,7 +18136,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 28, + "component_count": 27, "review_unit_index": 2, "review_unit_count": 2, "status": "reviewed", @@ -18175,12 +18163,12 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "fda16f21f2adab15e892d6b9062578a0fcc449d5f29a592f50b94644df9abc8d", + "prepared_review_unit_hash": "f8289d5d8bf2c29c753919e576ebb1aaef62317e4a6a4a3d23943021fe71c3fe", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84897, + "serialized_chars": 84899, "estimated_input_tokens": 21225, "estimated_eval_tokens": 42706 }, @@ -18188,57 +18176,57 @@ "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17124, - "estimated_input_tokens": 4281, - "estimated_eval_tokens": 8818 + "serialized_chars": 17127, + "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 are all model-specific migrations to standardized output tracing/capture APIs, but they affect different architectures and code paths. They are stylistically related, not duplicates; none of the soft-edge pairs should be merged as one change.", - "confidence": 0.92, + "summary": "These PRs are all model-specific refactors to adopt standardized output capturing/decorators, but they touch different model code paths and are not duplicates of one another. The shared theme is architectural cleanup, not one underlying bug or change.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44073 is a clean representative of the shared migration pattern: it updates one model file to use can_return_tuple/capture_outputs and defines the output-recording map without extra scope.", + "canonical_pr_reason": "Best representative is PR 44073: it shows the standard pattern clearly in a single model file and is a straightforward example of the output-tracing refactor theme.", "best_issue_reason": null, - "best_pr_reason": "PR 44129 is the strongest standalone candidate because it has an explicit issue link, a concrete SpeechT5 output-tracing refactor, and a more substantial implementation than the smaller template-like migrations.", + "best_pr_reason": "PR 44073 is the cleanest representative of the cluster\u2019s refactor pattern; however, none of these PRs are mergeable as duplicates because each targets a different model implementation.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Both are standardized output-tracing refactors, but for different models (FocalNet vs ImageGPT) and different code paths; they are not the same underlying bug/change." + "reason": "Both are output-tracing refactors, but they modify different models (FocalNet vs ImageGPT) and different concrete code paths. Same maintenance theme, not the same change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Same refactor theme, but different models and files (VisualBert vs TextNet); too broad to count as one duplicate change." + "reason": "Both move models toward standardized output capture, but VisualBERT and TextNet are separate implementations with different refactor details and tests. Not one underlying bug/change." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "Different model implementations (MPNet vs VisualBert) with model-specific output-hook wiring; not a single fix that could be merged into one PR." + "reason": "MPNet and VisualBERT each change their own output-capture wiring. The similarity is the refactor pattern, not shared functionality or a single fix." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "Both touch output tracing, but on unrelated models (MPNet vs TextNet) and separate forward/output contracts." + "reason": "These are separate model refactors in unrelated code paths; they do not look like one PR could plausibly subsume the other." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are unrelated model-specific migrations; the similar decorator/capture changes do not indicate the same concrete issue." + "reason": "RegNet and SqueezeBERT are distinct models with different output-handling implementations. The overlap is only the standardized decorator migration." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and SpeechT5 are different architectures with different forward signatures and output handling; this is not one mergeable fix." + "reason": "SqueezeBERT and SpeechT5 both touch output tracing, but they target different layers/models and different concrete behavior. They are not duplicates." } ] }, @@ -18252,7 +18240,7 @@ { "label": "pull_request", "component_index": 15, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18318,12 +18306,12 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "7726a9c3e7de776874413458dc82a9b59acebefce80af5360d72d3f7b1094082", + "prepared_review_unit_hash": "ddf9bec995d1bc564e0707151d74a449bd1d51e489547a2df6f70c93c21daf91", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40178, + "serialized_chars": 40179, "estimated_input_tokens": 10045, "estimated_eval_tokens": 20346 }, @@ -18331,7 +18319,7 @@ "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40178, + "serialized_chars": 40179, "estimated_input_tokens": 10045, "estimated_eval_tokens": 20346 }, @@ -18340,258 +18328,252 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "A cluster of similarly named output-tracing refactors across many unrelated model families. They share a tooling/style theme, but the PRs target different concrete forward paths and should not be deduplicated together.", - "confidence": 0.91, + "summary": "This cluster is a set of similarly titled but model-specific PRs refactoring output tracing across unrelated architectures. They share the same general theme, but not the same concrete code path, so none of the soft edges should be treated as duplicates.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44003 is the most representative cluster member: it makes the core output-tracing change with can_return_tuple/capture_outputs machinery and spans two closely related Mamba-family model files.", + "canonical_pr_reason": "No single true canonical PR: each PR targets a different model implementation. If a representative is needed, 44025 is the broadest example because it spans two closely related Depth Anything files, but it is not a duplicate of the others.", "best_issue_reason": null, - "best_pr_reason": "PR 44003 is the strongest single representative because it changes the actual tracing infrastructure rather than just a small per-model signature cleanup.", + "best_pr_reason": "44025 is the strongest representative of the theme because it has the broadest local scope and clear output-tracing refactor work, but the set is not a duplicate cluster.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Same refactor theme, but timm_backbone and upernet are different model paths; not the same concrete bug/change." + "reason": "Different model families and files (timm_backbone vs upernet); same refactor theme only, not the same code-path change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different model families and forward implementations; only the output-tracing style matches." + "reason": "Different architectures and modules (timm_backbone vs vision_text_dual_encoder); only the refactor pattern matches." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Separate model codepaths; this is a shared refactor pattern, not one duplicate fix." + "reason": "Different model implementations (timm_backbone vs univnet); not the same concrete bug or change." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Timm backbone output handling vs Mamba/FalconMamba tracing infrastructure are distinct changes in different subsystems." - }, - { - "left": "pull_request:43998", - "right": "pull_request:44004", - "accept": false, - "reason": "Different model families and signatures; same broad cleanup theme only." + "reason": "timm_backbone and mamba/falcon_mamba are unrelated code paths; too broad to be duplicates." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Unrelated concrete forward paths (timm_backbone vs rwkv); not one underlying bug." + "reason": "Different models and output logic; similarity is only at the generic tracing-refactor level." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "MobileNetV1 and UnivNet are separate model implementations; similar refactor, different code paths." + "reason": "MobileNetV1 and UnivNet are unrelated models; same refactor motif, not the same fix." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different models and outputs; not the same fix." + "reason": "Different model families and changed files; no shared concrete code path." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "MobileNetV1 and DepthAnything are unrelated model families; shared tracing refactor only." + "reason": "MobileNetV1 and Depth Anything are unrelated model implementations; do not merge on theme alone." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different model wrappers in different modalities; not a single concrete change." + "reason": "Different wrapper/model code paths; both are output-tracing refactors only in a broad sense." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "MobileNetV1 vs SpeechEncoderDecoder are distinct implementations and forward paths." + "reason": "MobileNetV1 vs speech_encoder_decoder are different code paths; 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 codepaths." + "reason": "Vision-text dual encoder and UnivNet are unrelated model code paths; same refactor style only." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different models; same refactor style does not make them duplicates." + "reason": "Different architectures (vision-text dual encoder vs upernet); no duplicate evidence beyond output-tracing cleanup." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Vision-text dual encoder forward cleanup is separate from Mamba tracing/output capture changes." + "reason": "Different model families and files; not plausibly one merged PR." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Different model families and different forward behavior; only broadly similar output-tracing cleanup." + "reason": "Distinct model implementations and code paths; generic similarity is insufficient." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet have different concrete forward paths; not the same bug/change." + "reason": "UnivNet and UperNet are unrelated models; same refactor pattern only." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "UnivNet output typing cleanup is unrelated to Mamba-family output recording." + "reason": "UnivNet vs Mamba/Falcon Mamba are different code paths; not the same concrete fix." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Different model families; this is not one mergeable fix." + "reason": "Different model implementations; no shared bug or change beyond refactoring output capture." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "UperNet and RWKV are unrelated model paths despite similar tracing cleanup." + "reason": "UperNet and RWKV are unrelated architectures; not the same underlying issue." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Separate codepaths and mechanisms; not the same concrete change." + "reason": "Different model families and changed files; too broad to merge as duplicates." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Mamba-family tracing infrastructure and SuperPoint feature output tracing are different implementations." + "reason": "Mamba/Falcon Mamba vs SuperPoint are unrelated code paths; same refactor pattern only." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Mamba output-capture refactor and CodeGen forward-signature cleanup are distinct code paths." + "reason": "Different model implementations and semantics; not the same concrete bug or change." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen are unrelated models; same high-level pattern only." + "reason": "Timm backbone and CodeGen are unrelated code paths; output-tracing cleanup alone is not enough." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "Different models and forward contracts; not a duplicate fix." + "reason": "UnivNet and CodeGen are unrelated models; not a duplicate change." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "UperNet segmentation output cleanup is unrelated to CodeGen's forward refactor." + "reason": "UperNet and CodeGen are unrelated implementations; same broad refactor theme only." }, { "left": "pull_request:44000", "right": "pull_request:44004", "accept": false, - "reason": "Different model families and bugs; only both touch output handling." + "reason": "Vision-text dual encoder and CodeGen are different code paths; do not conflate on pattern similarity." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "DepthAnything and VisionEncoderDecoder are separate model families; not one concrete bug/change." + "reason": "Depth Anything and VisionEncoderDecoder are different model code paths; not the same fix." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Different encoder-decoder/depth model codepaths; similar refactor theme only." + "reason": "Depth Anything vs SpeechEncoderDecoder are unrelated architectures; similarity is only at the refactor level." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "DepthAnything vs SuperPoint are unrelated model implementations." + "reason": "Depth Anything and SuperPoint are distinct model implementations; not duplicates." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Different model families and tracing mechanisms; not a single duplicate PR." + "reason": "Depth Anything and RWKV are unrelated code paths; no shared concrete bug." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "DepthAnything and DPR are unrelated codepaths." + "reason": "Depth Anything and DPR are different model families; not the same underlying change." }, { "left": "pull_request:44026", - "right": "pull_request:44027", + "right": "pull_request:44029", "accept": false, - "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are separate wrappers; similar cleanup, not the same fix." + "reason": "VisionEncoderDecoder and RWKV are unrelated implementations; generic tracing refactor only." }, { "left": "pull_request:44026", - "right": "pull_request:44028", + "right": "pull_request:44027", "accept": false, - "reason": "Different model families and forward paths; only the refactor pattern is shared." + "reason": "VisionEncoderDecoder vs SpeechEncoderDecoder are separate wrappers and code paths; not a duplicate." }, { "left": "pull_request:44026", - "right": "pull_request:44029", + "right": "pull_request:44028", "accept": false, - "reason": "VisionEncoderDecoder and RWKV are unrelated concrete codepaths." + "reason": "Different models and semantics; same high-level refactor theme is insufficient." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Different model families; not a mergeable duplicate." + "reason": "VisionEncoderDecoder and DPR are unrelated code paths; not the same bug or change." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "SpeechEncoderDecoder and SuperPoint are distinct models with different output semantics." + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated model implementations; not mergeable as one PR." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Separate model implementations; same broad tracing cleanup only." + "reason": "SpeechEncoderDecoder and RWKV are different code paths; only broadly similar output-tracing cleanup." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "SpeechEncoderDecoder and DPR are unrelated forward paths." + "reason": "SpeechEncoderDecoder and DPR are unrelated models; no duplicate evidence." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint feature extraction and RWKV language modeling are different concrete changes." + "reason": "SuperPoint and RWKV are unrelated architectures; not the same concrete fix." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Different models and output contracts; not the same underlying bug/change." + "reason": "SuperPoint and DPR are different model code paths; too broad to merge." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR are unrelated model codepaths despite similar output-tracing refactors." + "reason": "RWKV and DPR are unrelated models; same refactor motif only." } ] }, @@ -18605,7 +18587,7 @@ { "label": "pull_request", "component_index": 16, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18624,52 +18606,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "c6e605e132c901bafb2a47dc58dd27255478decd8a31d986570e502201e25852", + "prepared_review_unit_hash": "a669c2b166671136c6245af9bbf42af40a65f874efe9c88c81a3bd9541133dcf", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10911, - "estimated_input_tokens": 2728, - "estimated_eval_tokens": 5712 + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10911, - "estimated_input_tokens": 2728, - "estimated_eval_tokens": 5712 + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three PRs are separate model-addition features that happen to touch shared Transformers registration/docs scaffolding, but they implement different model families and code paths: PenguinVL, DeepSeek-OCR-2, and Voxtral TTS. None of the soft pairs looks like a true duplicate or mergeable single PR.", - "confidence": 0.97, + "summary": "These are three separate model-integration PRs that only overlap on shared Transformers boilerplate (docs, auto maps, package registration). They target different models and different implementation code paths, so they should not be deduplicated together.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: these are distinct model implementations for different tasks/domains, so the shared auto/docs changes are generic integration work rather than the same change.", + "canonical_pr_reason": "No canonical PR: the PRs add different models (PenguinVL, DeepSeek-OCR-2, Voxtral TTS) rather than the same fix or feature.", "best_issue_reason": null, - "best_pr_reason": "No global best PR among these; each PR is a separate feature addition with different model-specific files, tests, and behavior.", + "best_pr_reason": "No single PR is a duplicate-matching canonical choice; if forced, none of these is a better representative than the others because they are distinct additions.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "PenguinVL vs Voxtral TTS are different models and tasks (vision-language vs text-to-speech); shared registration/docs files are only generic scaffolding." + "reason": "Different model families and code paths: PenguinVL vs Voxtral TTS. Shared auto-registration/doc scaffolding is not enough to treat them as the same change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "PenguinVL and DeepSeek-OCR-2 are different model families with different model-specific implementations; overlap is limited to common Transformers integration files." + "reason": "PenguinVL and DeepSeek-OCR-2 are separate model implementations with different files, configs, and tests; they only share generic Transformers integration boilerplate." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 (OCR/vision) and Voxtral TTS (speech generation) are unrelated concrete code-path changes despite sharing auto-registration patterns." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are unrelated model additions; the overlap is limited to common framework plumbing, not a shared bug or mergeable fix." } ] }, @@ -18683,7 +18665,7 @@ { "label": "pull_request", "component_index": 17, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18699,12 +18681,12 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "42bd542cb19c1b6f3faf2584c63ec9f6107815fc409e8323b8126763ea7ae325", + "prepared_review_unit_hash": "47b213b641135d53d46a56ff5512841aa2b9f93c37f0609ddaad12d39c9864b2", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4407, + "serialized_chars": 4408, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -18712,7 +18694,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4407, + "serialized_chars": 4408, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -18721,18 +18703,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related in the broad area of module/kernel fusion, but they are not the same underlying change. PR 44979 introduces a new generic Module Fusion API and tests, while PR 45363 wires KernelConfig-based n-to-1 kernel fusion into model loading and adds an example. They target different code paths and should not be deduplicated.", - "confidence": 0.91, + "summary": "Two related but distinct pull requests about fusion machinery: one introduces a standalone Module Fusion API, while the other adds KernelConfig-based n-to-1 kernel fusion integration. They share the same broad theme but are not the same change.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44979 is the better canonical representative for the cluster because it defines the foundational fusion API and test coverage, making it the broader and more central change.", + "canonical_pr_reason": "PR #44979 is the cleaner canonical representative of the cluster because it introduces the core Module Fusion API itself and dedicated tests, whereas #45363 is a separate KernelConfig-based integration/follow-up feature.", "best_issue_reason": null, - "best_pr_reason": "PR 44979 is the best single PR to represent the topic because it is the core API addition; PR 45363 is a downstream integration of a specific kernel-fusion workflow built on top of that idea.", + "best_pr_reason": "PR #44979 is the best overall anchor for this cluster: it is the most foundational and self-contained fusion API change, with a clearer core abstraction than the more specific integration-oriented PR.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Related topic, but not the same concrete change: 44979 adds a generic Module Fusion API and tests, while 45363 adds KernelConfig-based n-to-1 kernel fusion integration plus an example. Different files, different code paths, and not plausibly one merged PR." + "reason": "Not a duplicate: #44979 adds a new Module Fusion API in src/transformers/module_fusion.py, while #45363 implements n-to-1 kernel fusion via KernelConfig across integrations/modeling utilities. Same general area, but different concrete code paths and mergeable as separate PRs." } ] }, @@ -18746,7 +18728,7 @@ { "label": "pull_request", "component_index": 18, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18762,12 +18744,12 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "3b2f1a09414102c743f19b6b6c0037f30315a655fbf81fa8f0539e60a6ee2300", + "prepared_review_unit_hash": "813d3968a95b60d92103e2a713329349603a5f3c0c8e3a3df9035ed10e04c1f4", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4414, + "serialized_chars": 4413, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -18775,7 +18757,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4414, + "serialized_chars": 4413, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -18784,18 +18766,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs address the same AttributeError in `_patch_mistral_regex` by switching to `tokenizer.pre_tokenizer`; PR 45317 is the more complete version because it includes the same fix plus tests.", - "confidence": 0.97, + "summary": "Both PRs address the same AttributeError in `_patch_mistral_regex` by switching from `backend_tokenizer.pre_tokenizer` to `tokenizer.pre_tokenizer` on the same code path; 45317 is the more complete patch because it adds tests.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the best canonical PR because it contains the same code fix as 45086 and adds test coverage, making it the more complete implementation of the bugfix.", + "canonical_pr_reason": "pull_request:45317 is the better canonical PR: it fixes the same bug as 45086 and includes test coverage, making it the more complete change set.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 is the strongest representative of the cluster: same concrete code-path fix, same target issue, and added regression tests.", + "best_pr_reason": "pull_request:45317 is the strongest overall PR candidate because it targets the same concrete fix and adds verification tests.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying AttributeError in `_patch_mistral_regex` with identical core code change; 45317 looks like a superset of 45086 by adding tests, so they could plausibly be merged into one PR." + "reason": "Same underlying AttributeError fix in `_patch_mistral_regex` on the same line-level code path; 45317 is essentially the test-backed version of 45086." } ] }, @@ -18809,7 +18791,7 @@ { "label": "pull_request", "component_index": 19, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18825,7 +18807,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "276afbe02a2c10ab698384b39ac86807b567382d2e674cbb6c5fd34f83846135", + "prepared_review_unit_hash": "b300943dd8c077366de12d30b0175623503f631d705351aa2a4a20d23eb0d395", "component_budget": { "node_count": 2, "item_count": 2, @@ -18847,18 +18829,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target NemotronH, but they are not the same change: #45115 is a focused inheritance/conversion-mapping refactor, while #45569 is a broader model split with new dense/sparse classes, docs, auto-mapping, and tests. They overlap in shared NemotronH core files, but do not look mergeable into a single PR as-is.", - "confidence": 0.92, + "summary": "Two open PRs touch the Nemotron H family, but they are not the same change: one refactors the base NemotronH conversion/model wiring, while the other splits Nemotron H into dedicated dense/sparse model variants and updates docs/tests.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45569 is the broader, more complete NemotronH follow-up: it introduces the dense/sparse model split, updates docs/auto-mappings, and includes tests, so it better represents the full architecture change.", + "canonical_pr_reason": "PR #45569 is the better canonical representative because it makes the larger, user-facing architectural change: it adds dedicated NemotronHDense/NemotronHSparse implementations, updates auto-mapping and docs, and includes tests. PR #45115 is a narrower refactor focused on inheritance and conversion mapping.", "best_issue_reason": null, - "best_pr_reason": "PR #45569 is the best representative of the cluster because it subsumes the smaller refactor with a wider, end-to-end NemotronH restructuring rather than just the conversion/inheritance portion.", + "best_pr_reason": "PR #45569 is the strongest standalone PR in this cluster: it is broader, more complete, and defines the new model variants rather than only adjusting internal refactor/conversion behavior.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Same model family, but different concrete changes: #45115 is mainly a conversion/inheritance refactor, whereas #45569 adds separate dense/sparse implementations plus docs and tests. They overlap in shared files but are not the same underlying PR-worthy fix." + "reason": "They overlap on NemotronH internals, but #45115 is a targeted refactor/conversion-mapping change while #45569 introduces separate dense/sparse model classes plus docs/tests. They are related, not the same concrete fix or mergeable duplicate." } ] }, @@ -18872,7 +18854,7 @@ { "label": "pull_request", "component_index": 20, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18888,7 +18870,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "5ff73d4efd88ce66d5b05be3a5027cbf6038ae8bc45b0d183941abf0c4212afd", + "prepared_review_unit_hash": "91687fd88fd34a50a5924668adad801021097794aef37634c691623be60c9ac5", "component_budget": { "node_count": 2, "item_count": 2, @@ -18910,18 +18892,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related but not duplicates: PR #45333 adds heterogeneous per-layer config support, while PR #45332 builds on that with broader heterogeneous modeling/cache changes. They share infrastructure files, but they do not appear to fix the same concrete bug or implement the same change.", - "confidence": 0.86, + "summary": "Two related but distinct feature PRs: one adds per-layer heterogeneous config plumbing, the other adds broader heterogeneous model/runtime support. They overlap in shared config helpers and tests, but they are not the same underlying change.", + "confidence": 0.81, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR fits a duplicate cluster here; #45332 is the broader end-to-end implementation, while #45333 is a narrower config-only foundation rather than the same change.", + "canonical_pr_reason": "PR 45332 is the broader, more central change: it extends heterogeneous support into cache/modeling code paths and includes the config integration needed for runtime use.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the better representative of the cluster because it covers the larger heterogeneous-model support surface and includes the runtime/modeling changes, whereas #45333 is only the configuration layer.", + "best_pr_reason": "PR 45332 is the best representative because it covers the end-to-end heterogeneous model support, while PR 45333 is narrower config-only plumbing that looks like a component of the larger feature.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Do not merge as duplicates: #45333 introduces per-layer config support, but #45332 extends into modeling/cache behavior and broader heterogeneous model plumbing. They are connected, yet not the same concrete code-path fix or single PR-sized change." + "reason": "They share heterogeneous config helpers, but one is a config-layer PR and the other is a broader modeling/runtime PR. They touch related infrastructure, not the same concrete bug or mergeable fix." } ] }, @@ -18935,7 +18917,7 @@ { "label": "pull_request", "component_index": 21, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18951,7 +18933,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "9990fc3ad92bea51838183367f4ded85dbcb3878332ead152e5c1eed92b42fcb", + "prepared_review_unit_hash": "e5c9f75a66569ee4b7630071ed8aea8cb1c35ae12983fa93c75d87ecad772e36", "component_budget": { "node_count": 2, "item_count": 2, @@ -18973,18 +18955,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are typing-related, but they target different changes: one is a broad type-checking sweep across many files, while the other adds specific typing protocols/aliases around modeling_utils and related helpers. They are not the same underlying fix and should not be merged as duplicates.", - "confidence": 0.91, + "summary": "These are both typing-related PRs, but they address different concrete changes: one is a broad type-checking sweep across many transformer modules, the other adds shared typing aliases/protocols and related model utility updates. They are similar in theme but not duplicates.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:45425 is the better representative because it is a narrower, more concrete typing change centered on _typing.py/modeling_utils support, whereas pull_request:45415 is a broad repo-wide type-checking pass.", + "canonical_pr_reason": "PR 45415 is the broader umbrella typing sweep and is the more representative canonical PR for this cluster; PR 45425 is a narrower follow-up focused on shared typing helpers and related model utility adaptations.", "best_issue_reason": null, - "best_pr_reason": "pull_request:45425 is the more canonical PR for this cluster: it has a focused purpose and a coherent code-path change, while pull_request:45415 is a large mixed typing sweep that is too broad to represent the same work.", + "best_pr_reason": "PR 45415 is the best overall representative because it covers the wider type-checking effort across `src/transformers/*py`, whereas PR 45425 is a more specialized support change.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Related only by general typing cleanup and a few shared files; 45415 is a broad type-checking pass, while 45425 adds specific typing protocols/aliases for modeling_utils and adjacent code. They do not fix the same concrete bug and are not mergeable as one PR." + "reason": "Same general typing initiative, but not the same underlying change. 45415 is a broad per-file typing cleanup; 45425 introduces shared typing protocols/aliases and utility updates. They would not naturally merge into one PR without conflating distinct work." } ] }, @@ -18998,7 +18980,7 @@ { "label": "pull_request", "component_index": 22, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19023,70 +19005,70 @@ "pull_request:45858|pull_request:45926", "pull_request:45890|pull_request:45926" ], - "prepared_review_unit_hash": "242f51b1ddb7b22b7cd633c3d815f4d8df2eaa6856052913de232d6c3a437efb", + "prepared_review_unit_hash": "d8f7e8e45f5618f4dd5268bd5980e2cabd5dfdddee41c9ae38224ab1fc10bf92", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 6, - "serialized_chars": 14716, - "estimated_input_tokens": 3679, - "estimated_eval_tokens": 7614 + "serialized_chars": 14720, + "estimated_input_tokens": 3680, + "estimated_eval_tokens": 7616 }, "budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 6, - "serialized_chars": 14716, - "estimated_input_tokens": 3679, - "estimated_eval_tokens": 7614 + "serialized_chars": 14720, + "estimated_input_tokens": 3680, + "estimated_eval_tokens": 7616 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "No true duplicate PRs here. The set splits into unrelated model-parallel fixes for different models and unrelated XPU test expectation updates for different models. The strongest single PR is the Gemma4 parallel fix.", - "confidence": 0.91, + "summary": "These PRs are mostly unrelated model-parallel fixes or model-specific XPU test expectation updates. None are true duplicates of each other; the only broad resemblance is that several touch device-placement/model-parallel behavior or add XPU test data, but they target different models and code paths.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45817 is the cleanest focused code fix: it addresses a concrete Gemma4 model-parallel device-placement bug and updates the relevant no-split module list in one localized change.", + "canonical_pr_reason": "No PR here is a clear duplicate of another. If one must be the cluster representative, #45487 is the broadest substantive fix and the most likely source of the shared model-parallel theme across the set.", "best_issue_reason": null, - "best_pr_reason": "PR 45817 is the best representative because it targets one specific code path with a small, plausibly mergeable fix and clear bug context.", + "best_pr_reason": "#45487 is the strongest representative because it fixes a real model-parallel bug across several model implementations, while the others are narrower, model-specific fixes or test-only expectation updates.", "soft_edge_verdicts": [ { "left": "pull_request:45487", "right": "pull_request:45843", "accept": false, - "reason": "Both mention model-parallel issues, but they fix different models and different code paths; not the same underlying bug." + "reason": "Both are model-parallel themed, but they target different models and different code paths. Not the same concrete bug." }, { "left": "pull_request:45487", "right": "pull_request:45926", "accept": false, - "reason": "AltCLIP/ChineseCLIP model-parallel fix vs HyperCLOVA XPU test expectations; unrelated changes." + "reason": "AltCLIP/ChineseCLIP model-parallel fixes are unrelated to HyperCLOVAX XPU test expectations." }, { "left": "pull_request:45817", "right": "pull_request:45843", "accept": false, - "reason": "Gemma4 device-placement fix and Deimv2 refactor/fix are model-specific and not mergeable into one PR." + "reason": "Gemma4 parallel fixes and DEIMv2 parallel fixes are separate model implementations with different changes; too broad to merge as one duplicate." }, { "left": "pull_request:45858", "right": "pull_request:45890", "accept": false, - "reason": "Both add XPU expectations, but for different models and different test files; these are separate changes." + "reason": "Both are test-only XPU expectation updates, but for different models and different logits; not the same underlying change." }, { "left": "pull_request:45858", "right": "pull_request:45926", "accept": false, - "reason": "Different models, different expectations, and different test targets; not the same change." + "reason": "Different model test suites with separate expected outputs; they do not fix the same concrete issue." }, { "left": "pull_request:45890", "right": "pull_request:45926", "accept": false, - "reason": "Same broad theme of XPU test updates, but the concrete models and outputs differ, so this is not a duplicate." + "reason": "Both update XPU expectations, but for different model-specific tests and values; not a duplicate change." } ] }, @@ -19100,7 +19082,7 @@ { "label": "pull_request", "component_index": 23, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19116,7 +19098,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "c9cd2bef4e84d295917cb63f229628e68da713b3f114a54dad075681701fa4c3", + "prepared_review_unit_hash": "f11aef75637129d1066526d9c6c55b5f3909f7f6eab4b93aa67c809efc62d0d3", "component_budget": { "node_count": 2, "item_count": 2, @@ -19138,18 +19120,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related EP-loading fixes, but they address different underlying bugs and code paths: one is about DeepSpeed ZeRO-3/accelerate launch serialization of distributed_config, the other about FSDP2/rank-0 broadcast overwriting experts during loading. Not duplicates.", - "confidence": 0.88, + "summary": "Two separate EP-related loading fixes: 45548 preserves distributed_config and adds has_ep, while 45662 fixes DTensor/EP parameter loading so experts are not overwritten during load. They overlap in modeling_utils but target different code paths and failure modes.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "45662 is the more concrete and complete fix for the actual parameter-loading overwrite path, with coordinated changes across loading and MoE/tensor-parallel code.", "best_issue_reason": null, - "best_pr_reason": "PR 45662 is the stronger representative of the cluster: it fixes a concrete parameter-loading overwrite path in core loading/moe integration and spans the exact EP/FSDP2 bug it describes.", + "best_pr_reason": "45662 is the stronger representative PR because it addresses a specific runtime corruption bug rather than only plumbing for EP configuration.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Both concern EP loading, but the bugs differ: 45548 fixes distributed_config/accelerate ZeRO-3 loading, while 45662 fixes rank-0 broadcast overwriting experts under FSDP2. Different root causes and merge targets." + "reason": "Both involve expert parallelism, but 45548 fixes config serialization/feature detection for ZeRO-3 loading, while 45662 fixes a different DTensor/FSDP2 overwrite issue during parameter assignment. They would not plausibly merge into one PR." } ] }, @@ -19163,7 +19145,7 @@ { "label": "pull_request", "component_index": 24, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19179,12 +19161,12 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "419cc8e32ee3e0ed3d8425ee27a6f78d748fef721cdcdef38098a33960246ec5", + "prepared_review_unit_hash": "9e6b0e7b45812b0f96e8705d7e5840e85af89d12216835e950352fadd7042def", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4590, + "serialized_chars": 4589, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -19192,7 +19174,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4590, + "serialized_chars": 4589, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -19201,18 +19183,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs address the same xdist/captured_info collision problem and target the same issue; 45645 is the more complete fix because it includes the library change plus CI log handling for multiple captured_info files.", - "confidence": 0.87, + "summary": "Both PRs target the same xdist/captured_info debugging-log problem under issue 45561; PR 45645 is the broader, more complete fix and subsumes the core change in 45639.", + "confidence": 0.86, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the most representative and complete version of the fix: it covers the xdist-safe output path change and updates CI artifact handling to read all captured_info files, matching the broader problem described in the title.", + "canonical_pr_reason": "PR 45645 is the best canonical representative because it includes the same testing_utils xdist-safe fix as 45639 and also updates the CI/workflow handling needed to preserve and aggregate the new per-worker log files.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 is the best single candidate because it addresses the full artifact-collision flow end to end, while 45639 is a narrower subset focused mainly on the testing helper.", + "best_pr_reason": "PR 45645 is the strongest overall candidate: it addresses the same concrete bug and extends the fix to the CI artifact-consumption path, making it the more complete merge target than 45639.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same underlying xdist captured_info collision fix, same target issue, and overlapping code paths in testing_utils; 45645 extends the same change to CI artifact consumption rather than introducing a separate problem." + "reason": "Accepted: both are about making captured_info debug logs safe under xdist for the same issue. 45645 appears to be a superset/broader implementation of the same underlying change, not a different fix." } ] }, @@ -19226,7 +19208,7 @@ { "label": "pull_request", "component_index": 25, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19289,7 +19271,7 @@ { "label": "pull_request", "component_index": 26, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19355,70 +19337,7 @@ { "label": "pull_request", "component_index": 27, - "component_count": 28, - "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-45975-2", - "nodes": [ - "pull_request:45975", - "pull_request:45977" - ], - "soft_pairs": [ - "pull_request:45975|pull_request:45977" - ], - "prepared_review_unit_hash": "73d639c4a69de481b801679348dc31513b77f65fb2c5363669d30dfd4150903e", - "component_budget": { - "node_count": 2, - "item_count": 2, - "soft_pair_count": 1, - "serialized_chars": 5479, - "estimated_input_tokens": 1370, - "estimated_eval_tokens": 2996 - }, - "budget": { - "node_count": 2, - "item_count": 2, - "soft_pair_count": 1, - "serialized_chars": 5479, - "estimated_input_tokens": 1370, - "estimated_eval_tokens": 2996 - }, - "overflow_policy": "truncate_then_skip", - "trimmed": false, - "aggressively_trimmed": false, - "split": false, - "analyst_result": { - "summary": "Both PRs are GGUF/Apple Silicon related, but they target different concrete changes: one adds an optional Metal dequant fast path via kernels-community, the other is a broader inference-time GGUF matmul/parity effort. They share only a utility file and broad theme, not the same underlying fix.", - "confidence": 0.91, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45977 is the broader and more central GGUF/Apple Silicon change, spanning core runtime, quantization, and benchmark coverage, so it is the better canonical representative of this cluster.", - "best_issue_reason": null, - "best_pr_reason": "PR 45977 is the best single representative because it captures the larger underlying Apple Silicon GGUF inference work, whereas 45975 is a narrower optional dequant path tweak.", - "soft_edge_verdicts": [ - { - "left": "pull_request:45975", - "right": "pull_request:45977", - "accept": false, - "reason": "Related in subsystem and platform, but not the same fix: 45975 is about optional kernels-community Metal dequant support, while 45977 is a broader GGUF matmul/inference parity effort with different code paths and scope." - } - ] - }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, - "error_kind": null, - "error_message": null - }, - { - "label": "pull_request", - "component_index": 28, - "component_count": 28, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19434,40 +19353,40 @@ "soft_pairs": [ "pull_request:45997|pull_request:46005" ], - "prepared_review_unit_hash": "e710f050324631b2044c18207a9161589c254ae27b0da9fd5dc8d4d6f466481f", + "prepared_review_unit_hash": "b1e17f5872fa5ba5683d68b4536022260189b774c7064f68fa2df4cd6bd51629", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4241, - "estimated_input_tokens": 1061, - "estimated_eval_tokens": 2378 + "serialized_chars": 4240, + "estimated_input_tokens": 1060, + "estimated_eval_tokens": 2376 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4241, - "estimated_input_tokens": 1061, - "estimated_eval_tokens": 2378 + "serialized_chars": 4240, + "estimated_input_tokens": 1060, + "estimated_eval_tokens": 2376 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same StaticLayer cache-length bug in src/transformers/cache_utils.py and share the same issue (#45987). PR 46005 is the broader fix and subsumes the storage-type change from PR 45997, so they are close enough to treat as one underlying change cluster.", - "confidence": 0.92, + "summary": "Both PRs address the same StaticLayer cache-length typing bug in `src/transformers/cache_utils.py` and target the same issue. PR 46005 is the more complete fix because it both scalarizes `cumulative_length` and normalizes `get_seq_length()` to return a plain int.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "46005 is the more complete fix: it converts cumulative_length to a 0-dim scalar tensor and also normalizes get_seq_length() to return a plain int, directly matching the bug description.", + "canonical_pr_reason": "`pull_request:46005` is the better canonical PR: it contains the core data-shape fix plus the API-side `get_seq_length().item()` correction, so it fully resolves the int-vs-tensor mismatch rather than only changing the stored tensor shape.", "best_issue_reason": null, - "best_pr_reason": "46005 best captures the full bug fix for issue 45987 because it addresses both the internal cache-length representation and the outward return type, whereas 45997 only changes the stored tensor shape.", + "best_pr_reason": "`pull_request:46005` is the best PR overall because it directly fixes the reported behavior end-to-end and is strictly more complete than `pull_request:45997`.", "soft_edge_verdicts": [ { "left": "pull_request:45997", "right": "pull_request:46005", "accept": true, - "reason": "Same underlying StaticLayer sequence-length bug, same file, same issue target, and 46005 is a superset of 45997 rather than a different fix; these could plausibly be merged into one PR." + "reason": "Same underlying bug in the same code path (`StaticLayer` cache length handling); the second PR is a superset-style refinement of the first, and they could plausibly be merged into one change." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index fdc8c9984c8ced1d66ec748428b32ad1cde50a96..d154da28384dfb4a69650169e3ae92d5cf467341 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260517t000046z", + "analysis_id": "hybrid-model-20260517t060024z", "archived_artifacts": { - "hybrid": "snapshots/20260517T000046Z/analysis-runs/hybrid-model-20260517t000046z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260517T000046Z/analysis-runs/hybrid-model-20260517t000046z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-17T00:04:02Z", + "published_at": "2026-05-17T06:03:48Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260517T000046Z", + "snapshot_id": "20260517T060024Z", "variant": "hybrid" } diff --git a/snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.json b/snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..87285e0116ac990153d6a9562bea72b23420d115 --- /dev/null +++ b/snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.json @@ -0,0 +1,2140 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260517T060024Z", + "generated_at": "2026-05-17T06:03:47Z", + "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-45987-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45987.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45987, + "canonical_pr_number": 46005, + "issue_numbers": [ + 45987 + ], + "pr_numbers": [ + 45997, + 46005 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45997, + "right_pr_number": 46005, + "code_similarity": 0.597, + "size_similarity": 0.737, + "file_overlap": 1.0, + "area_overlap": 0.35, + "patch_similarity": 0.182, + "shared_filenames": [ + "src/transformers/cache_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cache_utils.py", + "left_ranges": [ + [ + 290, + 302 + ] + ], + "right_ranges": [ + [ + 291, + 297 + ], + [ + 377, + 383 + ] + ] + } + ] + } + ] + }, + { + "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." + }, + { + "cluster_id": "cluster-45987-3", + "canonical_pr_number": 46005, + "duplicate_pr_numbers": [ + 45997 + ], + "target_issue_number": 45987, + "reason": "PRs in cluster-45987-3 are treated as duplicates because they converge on issue #45987 with closing_reference, shared_issue_target, soft_similarity 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/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..b9f0d434ff12459ff094233d96c9d5c914d11802 --- /dev/null +++ b/snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,19401 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260517T060024Z", + "generated_at": "2026-05-17T06:03:47Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "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:43425", + "issue:43531", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "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:45081", + "issue:45161", + "issue:45237", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45812", + "issue:45823", + "issue:45859", + "issue:45874", + "issue:45901", + "issue:45902", + "issue:45920" + ], + "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:45859|issue:45902", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:45823|issue:45874", + "issue:43425|issue:44292", + "issue:43828|issue:45161", + "issue:34928|issue:41720", + "issue:44918|issue:45161", + "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:41762|issue:43596", + "issue:43901|issue:44512", + "issue:39290|issue:41720", + "issue:45237|issue:45901", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:45812|issue:45920", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:39290|issue:43531", + "issue:41093|issue:43638" + ], + "prepared_review_unit_hash": "da6a3f199e7807061fab7cb571fb9b918b1be1615fe85a514fa79539e21d5134", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 62, + "serialized_chars": 46384, + "estimated_input_tokens": 11596, + "estimated_eval_tokens": 23448 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous, but it contains two clear duplicate subgroups: ZeRO-3/Bert index-out-of-bounds failures and the v5 AutoTokenizer wrong-token-ID regression. Most other pairs share a broad subsystem but look like distinct bugs or regressions.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45920 is the broadest and most representative issue in the tokenizer regression subgroup, covering multiple model families; issue:45812 looks like a narrower Granite-specific instance of the same v5 token-ID bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the best single anchor for the cluster because it captures the widest concrete bug pattern among the listed issues and is likely to subsume related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different failures: Qwen3.5 config attribute access vs streaming chat/completions handling." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Different model/runtime problems; shared GPU/MoE context is too broad to call duplicate." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Both are model-specific device/dtype issues, but with different models and failure modes." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Different concrete dtype/device mismatch cases; not the same bug." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "AMD loading issue vs GraniteMoEHybrid invalid-method call are unrelated code-paths." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different Qwen NVFP4 runtime error vs AMD GPU loading failure." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "Collective mismatch under DeepSpeed Zero3 vs ONNX export failure are unrelated." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Both are model/export related, but one is ONNX export and the other is FineGrainedFP8 runtime behavior." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export error and cudaErrorAssert during auto device mapping are different bugs." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 docs cleanup, but they target different removed features and likely separate edits." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export issue and GenerationMixin import breakage are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Similar-looking tensor/device errors, but different models and failure surfaces." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both mention index/mask shape failures, but the model/setup context is different enough that they do not clearly match." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Same general IndexError family, but one is ZeRO-3/Bert size-0 initialization and the other is a mask-shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Different problems: generic mask/tensor shape mismatch vs GPT-OSS MoE tensor-parallel failure." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Different model/trainer paths; no clear same underlying bug." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice_preset vs ModernBERT ONNX export are unrelated." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Different models and failure modes under DeepSpeed; not the same bug." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3/Bert index-0-out-of-bounds failure; the newer report is just a non-pretrained Bert variant." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger Kernel cross-entropy call vs GPT-OSS MoE tensor-parallel failure are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Different bugs: detokenization regression vs LoRA merge/save/load mismatch." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Quantized Qwen runtime error and LoRA merge mismatch are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation checkpointing/FSDP recomputation mismatch is not the same as a mask indexing error." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both involve DeepSpeed, but one is a 2-D weight training error and the other is a collective mismatch." + }, + { + "left": "issue:45859", + "right": "issue:45902", + "accept": false, + "reason": "Same Qwen3_5Moe embedding class, but one is CPU-offload incompatibility and the other is uninitialized-memory after materialization; not clearly the same bug." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "Both involve zero-3 / model-parallel contexts, but the specific failure paths differ." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Different model families and different runtime errors." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Different dtype/device issues in different models; too broad to merge." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch version compatibility and NVFP4 runtime error are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different model/runtime problems despite both being numerical/backend issues." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Video StopIteration in Qwen3-vl-embedding is unrelated to MPS histogram support." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Different failures in different code paths; only broad backend overlap." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch vs trainer signature change are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "FSDP activation-checkpointing mismatch and GenerationMixin import breakage are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Different runtime bugs; no shared concrete code path." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": false, + "reason": "Both are index-out-of-bounds under ZeRO-3, but different models and likely different root causes." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs issues: return_all_scores behavior vs removed run command reference." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Gemma3 sliding_window/vLLM attribute issue and Qwen3 auto device mapping cuda assert are different." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "Different product areas: AMD GPU loading vs table-question-answering crash." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure and device-mismatch forward error are not the same underlying bug." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger Kernel cross-entropy invocation and video StopIteration are unrelated." + }, + { + "left": "issue:45812", + "right": "issue:45920", + "accept": true, + "reason": "Same v5 AutoTokenizer wrong-token-ID regression; 45920 is the broader multi-model umbrella report." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Checkpoint corruption and NemotronH checkpoint-loading failure are different issues." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Unit-test load failure vs checkpoint corruption are not the same bug." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Different Qwen/Gemma sliding-window problems with distinct symptoms and models." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are shape/index errors, but the reported models and contexts differ enough that they do not clearly duplicate." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Dtype mismatch in Mistral-3 vs GraniteMoEHybrid invalid method call are unrelated." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Invalid method call in GraniteMoEHybrid vs MPS histogram unsupported type are different bugs." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different model families and different backend failures." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Different model/runtime contexts; not the same concrete bug." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Qwen NVFP4 runtime error and TRL SFT unpacking failure are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross-entropy call and TRL SFT trainer unpacking issue are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Both are ZeRO-3 index-out-of-bounds reports, but the model families and likely root causes differ." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions in v5, but they refer to different removed features and should not be merged as duplicates." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Different Qwen/Gemma sliding-window failures, not the same code-path problem." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Mask/index shape mismatch and ZeRO-3 Bert zero-size index error are different failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it identifies the two clearly supported duplicate subgroups (43596/43638 and 45812/45920) and otherwise treats the remaining pairs conservatively as likely distinct issues. The accepted soft-edge verdicts are supported by the issue titles and stay within the evidence available." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 2, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36010", + "issue:39186", + "issue:39290", + "issue:40990", + "issue:41093", + "issue:41762", + "issue:42915", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43645", + "issue:43716", + "issue:43792", + "issue:43828", + "issue:43866", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44530", + "issue:44589", + "issue:44841", + "issue:44918", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45084", + "issue:45161", + "issue:45362", + "issue:45399", + "issue:45464", + "issue:45542", + "issue:45632", + "issue:45685", + "issue:45698", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45901", + "issue:45902" + ], + "soft_pairs": [ + "issue:43792|issue:45901", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:43975|issue:45901", + "issue:43792|issue:45070", + "issue:45362|issue:45464", + "issue:44292|issue:45901", + "issue:39290|issue:45823", + "issue:43404|issue:43866", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:41093|issue:41762", + "issue:45800|issue:45823", + "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:45759|issue:45902", + "issue:40990|issue:44960", + "issue:43716|issue:44918", + "issue:39186|issue:44918", + "issue:45632|issue:45698", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:44530|issue:45005", + "issue:42915|issue:45399" + ], + "prepared_review_unit_hash": "760f2b5f3289c04cd12e4a07530fe4a5fc9b83dde8ab9e673816e6bd3fbe2de2", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 38765, + "estimated_input_tokens": 9692, + "estimated_eval_tokens": 19640 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue reports. The only near-match is the custom-module loading pair, but the available metadata is not enough to confirm a shared root cause, so it should stay tentative rather than merged as a duplicate.", + "confidence": 0.57, + "canonical_issue_reason": "Issue 45698 is the better anchor for the cluster: it states the broader from_pretrained/save_pretrained custom-module loading failure. Issue 45632 looks related, but the packet does not firmly establish that it is the same bug rather than a specific variant.", + "canonical_pr_reason": null, + "best_issue_reason": "Most actionable issue in the set: open and centered on a concrete custom-module loading path with a clear user-facing failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Both involve custom-module loading, but the evidence is too thin to prove the same underlying bug; one points to a cache-path collision, the other to wrong module selection after save/load." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Mostly conservative, but a bit too assertive for the evidence in the packet. The phrase \"open, clearly reproducible\" is not grounded by the supplied metadata alone, and the accepted 45632\u219445698 pairing is plausible but not strongly established beyond title similarity. Please keep the duplicate call softer unless the bodies explicitly show the same root cause." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 3, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:39692", + "issue:41553", + "issue:41628", + "issue:41762", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43493", + "issue:43643", + "issue:43644", + "issue:43782", + "issue:43828", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44492", + "issue:44512", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45237", + "issue:45507", + "issue:45520", + "issue:45663", + "issue:45701", + "issue:45800", + "issue:45859", + "issue:45902" + ], + "soft_pairs": [ + "issue:44360|issue:44512", + "issue:43873|issue:45005", + "issue:44863|issue:45005", + "issue:44492|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:44292|issue:45507", + "issue:39692|issue:43054", + "issue:43644|issue:43950", + "issue:43828|issue:44928", + "issue:36331|issue:41762", + "issue:41628|issue:45800", + "issue:43866|issue:44403", + "issue:43950|issue:45902", + "issue:43872|issue:44589", + "issue:43054|issue:45701", + "issue:41553|issue:43883", + "issue:38175|issue:43054", + "issue:44910|issue:45859", + "issue:45663|issue:45902", + "issue:41553|issue:43881", + "issue:42947|issue:44387", + "issue:43054|issue:43493", + "issue:44403|issue:44451", + "issue:43643|issue:45020", + "issue:43975|issue:45520", + "issue:43975|issue:45237", + "issue:44403|issue:44488", + "issue:42947|issue:43856", + "issue:43881|issue:43883", + "issue:41762|issue:42915", + "issue:43782|issue:44960" + ], + "prepared_review_unit_hash": "15c378b83f1c57bcf067669b20e229fb48e9ec7ffea7255ff33614baad816dc1", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36587, + "estimated_input_tokens": 9147, + "estimated_eval_tokens": 18550 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The duplicate cluster is mostly solid around the Transformers 5.x non-persistent-buffer regression: 43950, 43644, and 44534 all point to the same underlying corruption bug. Issue 45902 is related in the same area, but the packet only supports it as a narrower symptom, not a confirmed duplicate.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43950 is the best canonical representative because it describes the regression at the right level of generality\u2014`from_pretrained()` corrupting non-persistent buffers in Transformers 5.x\u2014and it is directly corroborated by 43644 and 44534. 45902 looks related, but this packet does not establish it as the same bug with enough certainty.", + "canonical_pr_reason": null, + "best_issue_reason": "43950 is the strongest issue anchor for triage: it names the broad regression clearly, matches the shared non-persistent-buffer failure mode, and cleanly subsumes the confirmed duplicates 43644 and 44534.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "Unrelated topics: a DSA indexer discussion vs a docs typo about a removed command." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is not the same bug as tied-weights handling in translation models." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading failure is a different problem from translation-model tied weights." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategy typo is unrelated to the removed transformers run command docs issue." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Different model/code-path failures: Qwen3.5 input embedding unpacking vs GraniteMoEHybrid invalid method calls." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Both are model-related, but they involve different models and concrete failures with no shared underlying bug shown." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Same underlying non-persistent-buffer regression; both titles describe the same junk/corruption behavior in Transformers v5." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "No shared bug: Qwen NVFP4 loading error vs GraniteMoEHybrid invalid method issue." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "Both mention SigLIP2, but one is a docs/example error and the other is a text-embedding quality discrepancy." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Direct duplicate reports of the same non-persistent-buffer junk/corruption regression." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Different models and failure modes: dtype mismatch under autocast vs Qwen3.5 position_ids/SDPA behavior." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Trainer API mismatch and Gemma3 DeepSpeed loading failure are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "Importing AutoImageProcessor and torch-version incompatibility are separate issues." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Checkpoint corruption is not the same as generic loading noise." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": false, + "reason": "The packet only shows a narrower uninitialized-memory symptom after `meta \u2192 to_empty(cuda)`; it does not clearly establish the same non-persistent-buffer regression." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Bitsandbytes unexpected-kwarg failure and missing Float8 storage type are different compatibility bugs." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "Both involve tokenization/model behavior, but the reported failures and likely root causes differ." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Bad AutoTokenizer error for Voxtral is unrelated to Molmo's tied-weights attribute error." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both concern SigLIP2, but unexpected zero probabilities and degraded text embeddings are different symptoms with no clear same root cause." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "Both are Qwen-related, but Flash Attention crash from 3D position_ids is different from CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states handling is a different bug from non-persistent-buffer materialization corruption." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Voxtral AutoTokenizer error and glm-4v loading failure are unrelated." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient checkpointing with PEFT LoRA and int4 memory/OOM regression are different training-performance issues." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": false, + "reason": "Both mention SigLIP2, but embedding quality and HF-vs-JAX implementation discrepancy are not the same bug." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading noise and a specific model load failure are different issues." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "A missing-fields bug in AutoConfig with trust_remote_code is not the same as broad remote_code breakage." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization of a specific model and a Python 3.13 flash_attn import KeyError are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Different models and failures; no shared underlying code-path problem is evident." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Two separate model-loading complaints with no concrete shared bug." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "LoRA gradient checkpointing and Qwen3 MoE memory usage are different training-performance problems." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "glm-4v loading and Molmo tied-weights attribute error are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 loading failure and Qwen3Moe FineGrainedFP8Config failure are separate model/config issues." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error and GLM5 are different model-loading failures." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The 43950/43644/44534 cluster is well grounded, but the 43950\u219445902 duplicate call is too strong given the packet. 45902\u2019s title only shows an uninitialized-memory issue after meta\u2192to_empty(cuda) materialization; the packet does not clearly establish that it is the same non-persistent-buffer regression. Because soft-edge verdicts need to stay conservative, I can\u2019t accept this as written." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 4, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36331", + "issue:41093", + "issue:41553", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43366", + "issue:43404", + "issue:43638", + "issue:43742", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43872", + "issue:43940", + "issue:43950", + "issue:44220", + "issue:44291", + "issue:44368", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44560", + "issue:44661", + "issue:44805", + "issue:44863", + "issue:44928", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45305", + "issue:45313", + "issue:45325", + "issue:45356", + "issue:45399", + "issue:45538", + "issue:45588", + "issue:45685", + "issue:45823", + "issue:45902", + "issue:45923" + ], + "soft_pairs": [ + "issue:45685|issue:45823", + "issue:42491|issue:44368", + "issue:43824|issue:43872", + "issue:45020|issue:45823", + "issue:44661|issue:45020", + "issue:44991|issue:45399", + "issue:43828|issue:45823", + "issue:45081|issue:45399", + "issue:43827|issue:44509", + "issue:45020|issue:45356", + "issue:43404|issue:43950", + "issue:43742|issue:45399", + "issue:42915|issue:45020", + "issue:43638|issue:45823", + "issue:43257|issue:43866", + "issue:43792|issue:44220", + "issue:43872|issue:44291", + "issue:42915|issue:43872", + "issue:43940|issue:45313", + "issue:41553|issue:44991", + "issue:43854|issue:44863", + "issue:36331|issue:41093", + "issue:43257|issue:45305", + "issue:42947|issue:45923", + "issue:44928|issue:45588", + "issue:43872|issue:45538", + "issue:41093|issue:44805", + "issue:41553|issue:44488", + "issue:44479|issue:44560", + "issue:44530|issue:44863", + "issue:24643|issue:30064", + "issue:45325|issue:45902", + "issue:43366|issue:43828" + ], + "prepared_review_unit_hash": "ebfd7b3d6b6706316dcf46caee9e35259dfa6eb8fddc944b4240d6d8bc325a14", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 38071, + "estimated_input_tokens": 9518, + "estimated_eval_tokens": 19292 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous model-loading/training regressions, with only a few true duplicates. The clearest duplicate groups are the docs cleanup around removed v5 pipeline tasks, the bitsandbytes/_is_hf_initialized init_empty_weights TypeError, and the identical mask/tensor shape IndexError reports.", + "confidence": 0.78, + "canonical_issue_reason": "44291 is the most precise report of the bitsandbytes/_is_hf_initialized regression, naming the exact failing path and version; it best serves as the canonical issue for that duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "44291 is the strongest standalone issue in the cluster: concrete, reproducible, and root-caused, unlike the broader or more speculative reports nearby.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "Different failures: MPS Int histogram support vs Gemma4 PLE device placement mismatch." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "Both mention Qwen/LoRA, but one is a hf4.x\u2192hf5.x compatibility break and the other is a tie_word_embeddings warning." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Unrelated bugs: missing Qwen2_5_VL import vs bitsandbytes Int8Params/_is_hf_initialized TypeError." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Too broad and different: remote_code regressions vs a device_map forward mismatch." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Different root causes: tokenizer mapping helper failure vs generic remote_code breakage." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer load failure for a specific model vs flash-attn fallback gating; no shared code-path." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Different runtime issues: autocast dtype mismatch vs device mismatch." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex crash vs flash-attn fallback blocking; unrelated fixes." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Both are the same docs regression after v5 pipeline removals; one is just a narrower phrasing of the same cleanup." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Both are regressions, but one is broad remote_code breakage and the other is a specific Kimi-K2.5 tokenizer codec/warning issue." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Different model bugs: untied lm_head weights vs non-persistent buffer corruption." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "Key error loading MobileLLM vs flash-attn fallback gating; no same underlying defect." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "Both are Qwen-related regressions, but one is a Qwen3_moe LoRA compatibility problem and the other is a generic remote_code breakage." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "Different code paths: DeepSpeed ZeRO-3/Bert IndexError vs Gemma4 device mismatch." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Different model-loading failures: Qwen3 MOE weight conversion vs Ovis2 checkpoint corruption." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Possible audio-processing relation, but the titles are not specific enough to treat as the same bug." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same bitsandbytes/_is_hf_initialized incompatibility; the second issue states the exact root cause and reproducer more clearly." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Both involve model/loading regressions, but they are different bugs with different failure modes." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Similar DeepSpeed ZeRO-3 symptoms, but different Qwen model families and different reported failure details." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer issues for different models; not the same underlying defect." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different model-specific loading failures with no shared error path." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Unexpected compute_loss kwarg vs tensor-mask shape mismatch; unrelated bugs." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Weight conversion under Accelerate/DeepSpeed vs gradient averaging under GAS; different layers of the stack." + }, + { + "left": "issue:42947", + "right": "issue:45923", + "accept": false, + "reason": "Both mention checkpointing, but one is LoRA checkpointing ineffective and the other is a missing model flag on a trust_remote_code variant." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "Different failures: RLHF gradient explosion/SDPA fallback vs flash_attention.py handling of sink-less models." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "bitsandbytes init error vs CLIPTokenizer max length constant; unrelated." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same mask/tensor shape mismatch error class with essentially identical failure message; these look like duplicate reports of the same indexing bug." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Both are tokenizer-related, but they concern different models and different failure modes." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-input regressions, but the affected models and errors differ enough to keep separate." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "PagedAttentionCache linear_attention group crash vs NemotronH checkpoint loading failure; not the same bug." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Training DeepSpeed weight-shape error vs image processor segmentation-map failure; unrelated." + }, + { + "left": "issue:45325", + "right": "issue:45902", + "accept": false, + "reason": "Different rotary/positioning bugs on different architectures; no shared fix path." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF gpt-oss support vs Phi-tiny-MoE autocast dtype mismatch; unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative overall. The three accepted duplicate pairs are defensible from the titles/body metadata: the docs pipeline-removal reports, the bitsandbytes/_is_hf_initialized TypeError reports, and the matching mask/tensor shape IndexError reports. No soft-edge verdict stands out as an overstatement, and the cluster-level summary matches the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 5, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36010", + "issue:38175", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42617", + "issue:42915", + "issue:43317", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43632", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43720", + "issue:43824", + "issue:43854", + "issue:43931", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44155", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44960", + "issue:44977", + "issue:45030", + "issue:45276", + "issue:45313", + "issue:45357", + "issue:45584", + "issue:45663", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:45663|issue:45823", + "issue:44155|issue:45584", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:43550|issue:44910", + "issue:43824|issue:43957", + "issue:43366|issue:44589", + "issue:42915|issue:43957", + "issue:43645|issue:43646", + "issue:44560|issue:44918", + "issue:42617|issue:43366", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:38175|issue:43994", + "issue:43632|issue:45834", + "issue:44560|issue:44805", + "issue:44877|issue:45030", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:43317|issue:44756", + "issue:43644|issue:44534", + "issue:38175|issue:39692", + "issue:44960|issue:44977", + "issue:42491|issue:43720", + "issue:45313|issue:45357", + "issue:41720|issue:42915", + "issue:44451|issue:44488", + "issue:42491|issue:45276", + "issue:42915|issue:44756", + "issue:43708|issue:44075", + "issue:43854|issue:43931" + ], + "prepared_review_unit_hash": "f24971b2b5c110f07a07ae8f1558b0fb5567ccbca900b5f3470c3a3788d50a86", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37191, + "estimated_input_tokens": 9298, + "estimated_eval_tokens": 18852 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated issues. Only two duplicate pairs look strong enough to merge: the two custom-model initialization regressions and the two non-persistent-buffer regression reports.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 44534 is the clearest canonical anchor for the non-persistent-buffer regression: it states the concrete Transformers v5 corruption bug directly and matches the near-verbatim duplicate 43644.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44534 is the best single issue to represent the strongest duplicate pair in this set because it names the exact bug class and is more precise than the alternate duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Same broad model family, but different failures: FSDP2 KeyError during training vs device-mismatch during forward. Not the same concrete bug." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "Different models and unrelated symptoms (batched AudioFlamingo3 leakage vs Whisper empty-transcription generation)." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Unrelated topics: GGUF/gpt-oss support vs Qwen3-MoE sliding_window behavior." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Both are loading/runtime issues, but one is a Transformers v5 buffer-corruption regression and the other is a long-OCR index error in Kosmos2.5." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different models and different attention paths (Bamba SDPA compile failure vs Qwen3.5 flash-attention crash)." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Import error for a specific class vs meta-device model-loading breakage; not the same bug." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "Support request vs storage-type/type-error regression; no shared underlying code-path." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Different problems: Qwen3-MoE FP8 failure vs generic torch.device(\"meta\") loading breakage." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These describe the same Transformers v5 custom-model initialization regression; one is just a notebook-specific reproduction of the same bug." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both mention Qwen, but one is a video embedding StopIteration and the other is an SFT-trainer unpacking failure; different code paths." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "No shared bug: inability to run a script vs GGUF architecture support." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "ImportError for GenerationMixin and Qwen3-MoE FP8 failure are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer-mapping edge case vs Gemma4 PLE device mismatch; different subsystems and failure modes." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but the evidence only shows similar bad outputs, not the same concrete bug or fix path." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "Transformers v5 _is_hf_initialized regression vs Kosmos2.5 OCR index error; unrelated." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Different failure modes and different model contexts; not the same bug." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both involve config validation, but the model targets and likely fixes differ; too weak to merge." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "DeepSpeed ZeRO-3/Bert indexing failure is unrelated to add-new-model-like tokenizer mapping behavior." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Different issues: ZeRO-3/Bert index error vs tokenizer-mapping failure." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer-mapping failure and a tensor mask shape mismatch are unrelated." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Different loading issues: gpu+cpu offload dequantization vs mmap OOM mitigation." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Near-verbatim duplicate reports of the same Transformers v5 non-persistent-buffer corruption regression." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Both involve SigLIP2, but one reports zero probabilities and the other a docs-example model/processor mismatch plus quantization failure; not enough evidence of one shared bug." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Completely different models and failures (GLM5 vs Qwen3.5 flash-attention generation)." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "LoRA/qwen3_moe version incompatibility and BitNet packed-weight loading are different bugs." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Different code paths and symptoms: ZeRO-3 weight loading vs save_pretrained key serialization." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Different models and failures: Qwen3 device-map cuda assert vs Qwen3-MoE FP8 config issue." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading complaints, but they involve different BERT models and there is no evidence they share the same underlying bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative on the soft edges. The two accepted pairs look reasonably mergeable for the same bugfix, and the rejected pairs are phrased cautiously rather than overstating shared causality. No obvious overclaiming." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 6, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44488", + "issue:44743", + "issue:44756", + "issue:44910", + "issue:44912", + "issue:44960", + "issue:44991", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:45488|issue:45812", + "issue:39692|issue:43994", + "issue:43257|issue:43854", + "issue:44488|issue:44991", + "issue:42491|issue:43931", + "issue:43856|issue:43873", + "issue:43644|issue:43645", + "issue:45362|issue:45406", + "issue:43856|issue:44387", + "issue:44910|issue:45588", + "issue:42491|issue:45292", + "issue:45276|issue:45335", + "issue:44164|issue:44291", + "issue:36010|issue:39404", + "issue:43404|issue:43454", + "issue:41720|issue:44155", + "issue:43425|issue:43957", + "issue:44402|issue:44488", + "issue:39692|issue:44960", + "issue:42947|issue:45704", + "issue:45663|issue:45759", + "issue:43335|issue:45663", + "issue:43873|issue:44387", + "issue:44291|issue:44756", + "issue:45663|issue:45859", + "issue:44155|issue:45823", + "issue:44292|issue:44912", + "issue:44387|issue:44756", + "issue:43854|issue:45216", + "issue:43957|issue:44756", + "issue:44743|issue:44960", + "issue:45276|issue:45292", + "issue:45684|issue:45698" + ], + "prepared_review_unit_hash": "8b6e105dd047439290cb11385c8f075ebbb2d04edf68d53cdd5ea94923fc8340", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37771, + "estimated_input_tokens": 9443, + "estimated_eval_tokens": 19142 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a grab-bag of unrelated model-specific Transformer regressions. The only clear duplicate-like subgroup is the `resize_token_embeddings` propagation bug around Gemma4/T5Gemma, so that is the best canonical thread; the rest should stay separate.", + "confidence": 0.73, + "canonical_issue_reason": "issue:45292 is the broadest statement of the `resize_token_embeddings` regression, and the Gemma4/T5Gemma reports look like model-specific manifestations of the same underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45292 is the cleanest representative of the only convincing duplicate cluster in this set; it generalizes the same embedding-resize failure that shows up in the related model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both involve tokenizer behavior, but they hit different model families and different failures: DeepSeek V3/R1 pre-tokenizer override vs Granite token-id regression." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Same SigLIP2 family, but one is a broken doc example with model/processor mismatch and quantization issues; the other is a model loading/pipeline output regression." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Completely different models and failure modes; Qwen3 MoE conversion under accelerate/deepspeed is not the same bug as GLM-4.7-Flash loading in tests." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading complaints, but they concern different models and likely different root causes, so this is too broad to merge." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "These are distinct Qwen3-related load problems: one is hf4.x\u2192hf5.x LoRA compatibility, the other is a shape mismatch for Qwen3-VL-30B." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both mention memory/quantization, but one is Qwen3 MoE training efficiency and the other is offloading failure with quantization; not the same concrete bug." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformers 5.0 regressions, but one is junk non-persistent buffers and the other is custom model initialization in Jupyter notebooks." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different model-specific crashes: Qwen3.5 chat crash versus Gemma4Processor missing `_tokenizer` in serve." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "These are both memory-related, but one is training memory inefficiency and the other is int4 quantization reserved-memory/OOM behavior." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both touch flash attention, but the root causes differ: packed-sequence misinterpretation of position_ids versus `s_aux=None` AttributeError." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "LoRA hf4.x\u2192hf5.x incompatibility is unrelated to the generic `resize_token_embeddings` output-embedding bug." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": true, + "reason": "Both describe the same `resize_token_embeddings` failure to update tied output/input embeddings, just surfaced in different model classes." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "One is save/from_pretrained mishandling `extra_state`; the other is `init_empty_weights` rejecting `_is_hf_initialized`." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "Importing `GenerationMixin` from `transformers.generation` and Whisper `return_language` pipeline behavior are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both mention lm_head tying, but they are different multimodal model classes with no evidence of the same exact code-path bug." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "These are unrelated: Qwen3 device-map cuda asserts versus AudioFlamingo3 batched track-state leakage." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch version incompatibility is a dependency issue, while the meta-device report is a model-loading regression in Transformers 5.x." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Both involve tokenizer/model vocab problems, but the specific models and symptoms differ, so this is not a clear duplicate." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "SigLIP2 doc/model issues are unrelated to the GLM5 report." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing with PEFT LoRA is unrelated to the T5/apex RMSNorm memory leak." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma-4 FSDP2 shared_kv_states behavior and Qwen multimodal `text_config` unwrapping are different model-integration bugs." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and Gemma-4 FSDP2 attention-state rebuilding are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Quantization/offloading behavior and int4 reserved-memory OOM are related only at a very broad level, not as the same bug." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "`init_empty_weights` argument handling and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Gemma-4 FSDP2 attention state handling and Qwen3_5Moe CPU-offload incompatibility are different issues." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 batched inference state leakage is unrelated to Gemma4 device-mismatch during forward." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Different quantization formats and failures: NVFP4 loading error versus MXFP4 fallback to bf16." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Both involve OOMs, but one is int4 reserved-memory growth and the other is disabling mmap on Strix Halo." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "GLM-4.7-Flash test loading and Qwen3.5 save_pretrained regression are separate model/load paths." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading regressions and Strix Halo mmap OOM are not the same bug." + }, + { + "left": "issue:44743", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3 recurrent-state reset with cache is unrelated to the GLM5 report." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "These are the same `resize_token_embeddings` defect, with 45276 being a model-specific manifestation and 45292 the broader report." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "`save_pretrained` permission propagation and `from_pretrained` loading the wrong custom module are different custom-model save/load problems." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only clearly supported duplicate cluster is the resize_token_embeddings trio around 45276/45292/45335, and the other soft-edge rejections avoid overclaiming sameness across different model-specific failures." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 7, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36032", + "issue:39404", + "issue:42947", + "issue:43257", + "issue:43299", + "issue:43381", + "issue:43425", + "issue:43452", + "issue:43596", + "issue:43611", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43716", + "issue:43828", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44265", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44671", + "issue:44683", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44928", + "issue:44991", + "issue:45084", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45701", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:42947|issue:43381", + "issue:44479|issue:44877", + "issue:43646|issue:43708", + "issue:45588|issue:45663", + "issue:45292|issue:45335", + "issue:43645|issue:44164", + "issue:44402|issue:44451", + "issue:43257|issue:44863", + "issue:43828|issue:43957", + "issue:43425|issue:43828", + "issue:44683|issue:45823", + "issue:44589|issue:44756", + "issue:39404|issue:45701", + "issue:43931|issue:44863", + "issue:43425|issue:45823", + "issue:43906|issue:44530", + "issue:43611|issue:43645", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:39404|issue:44912", + "issue:43901|issue:44509", + "issue:44265|issue:44898", + "issue:44479|issue:44805", + "issue:43994|issue:44079", + "issue:43299|issue:43931", + "issue:43425|issue:44918", + "issue:44589|issue:45084", + "issue:39404|issue:44671", + "issue:44164|issue:45759", + "issue:36032|issue:43452", + "issue:43596|issue:44683", + "issue:44671|issue:44991" + ], + "prepared_review_unit_hash": "859dd7b0156528b7b121dc0b6663950ccc58462cf636f9fe085dd04c5f7eeae3", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37968, + "estimated_input_tokens": 9492, + "estimated_eval_tokens": 19240 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a loose cluster of Transformers v5 regression reports, not one tight duplicate set. The only clear duplicate-like pairs are the two tokenizer-embedding resize issues and the two Qwen3-VL loading reports; the rest are related at a broad subsystem level but describe different bugs.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43611 is the broadest, most representative report of the v5 model-loading breakage theme in this cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best single issue to anchor the cluster because it captures the most general loading-regression pattern rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Both involve training/gradient behavior, but the eval-mode checkpointing restriction is a different bug than the Qwen3.5 NaN/SDPA fallback issue." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "Extra state handling in save/from_pretrained and disabling mmap on Strix Halo are unrelated failure modes." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both mention gradient checkpointing, but one is PEFT/LoRA effectiveness and the other is an eval-mode restriction; different code paths." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Video-input regression for Qwen/VL models and strict-config loading for granite_speech are different issues." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model init in Jupyter notebooks and Trainer resume/max_steps calculation are separate problems." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Flash-attention s_aux=None crash and Gemma4 FSDP2 shared_kv_states KeyError are not the same bug." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Both report resize_token_embeddings failing to update downstream output/decoder embeddings; same underlying embedding-resize bug." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Notebook-defined custom model initialization and extra_state serialization are different failure modes." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Tokenizer vocab-size mismatch and inability to load ScandiBERT are related to loading, but not the same concrete defect." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed and NemotronH checkpoint loading are separate model-loading regressions." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch and meta-device loading failures are different code-path problems." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility is too broad and not the same as the Phi-tiny-MoE autocast dtype mismatch." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Torch>=2.9 flex_attention compilation and Gemma4 PLE device-mapping mismatch are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup failure and mmap OOM on Strix Halo are distinct runtime issues." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper return_language pipeline regression and tokenizer-version-dependent tokenization changes are different symptoms and code paths." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and NemotronH checkpoint loading are different model families and bugs." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Generic Torch incompatibility and Gemma4 device mismatch are not the same bug." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "An isolated reproduction of a prior issue and a PagedAttentionCache linear_attention crash are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both are v5 custom-model loading regressions, but one is base_model_prefix handling and the other is notebook-defined initialization; not the same concrete bug." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Torch 2.10 incompatibility and Mistral-3 dtype mismatch are separate issues." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache group-type crash and template-node compilation error are different failures." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline behavior and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Docs drift for return_all_scores and docs for removed pipeline tasks are both documentation issues, but not the same one." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export export failure with torch_compilable_check and Perceiver non-default-resolution failure are different bugs." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Qwen video-input regression and a mask-shape IndexError are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "SigLIP2 nonsense predictions and ModelOutput key assignment are separate problems." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": true, + "reason": "Both concern Qwen3-VL / Qwen3VL model loading failing under v5, with shape-mismatch-style symptoms; same underlying loading regression is plausible." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch incompatibility and Qwen3.5 embedding unpacking are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup failure and non-template node compilation error are different issues." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline regression and CamemBERT masked-LM prediction regression are different model-specific bugs." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "Extra_state serialization and from_config text_config unwrapping are distinct loading/serialization issues." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5 tokenizer loading conflict and gguf_file breaking from_pretrained are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Deepspeed ZeRO3/BertModel index error and flex_attention compilation failure are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT prediction regression and tokenizer-loading failure for est-roberta are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately cautious. The stated duplicate-like pairs are supported by the issue titles, and the rejected pairs are conservative rather than overstated. I don\u2019t see a soft-edge verdict that clearly stretches the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 8, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42915", + "issue:43089", + "issue:43317", + "issue:43404", + "issue:43421", + "issue:43452", + "issue:43482", + "issue:43541", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43716", + "issue:43856", + "issue:43883", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44451", + "issue:44464", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44661", + "issue:44683", + "issue:44737", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45507", + "issue:45584", + "issue:45859", + "issue:45987" + ], + "soft_pairs": [ + "issue:32090|issue:39404", + "issue:43856|issue:44756", + "issue:44991|issue:45081", + "issue:44164|issue:44479", + "issue:44737|issue:45859", + "issue:43582|issue:43632", + "issue:44488|issue:45081", + "issue:44661|issue:44683", + "issue:44488|issue:44987", + "issue:40990|issue:43421", + "issue:43611|issue:43644", + "issue:44206|issue:44220", + "issue:43716|issue:45084", + "issue:43883|issue:44488", + "issue:43643|issue:44530", + "issue:36032|issue:42915", + "issue:44811|issue:45584", + "issue:34567|issue:40444", + "issue:44464|issue:45987", + "issue:44451|issue:44987", + "issue:43452|issue:43482", + "issue:43541|issue:45084", + "issue:43644|issue:43646", + "issue:42915|issue:44530", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:36032|issue:43645", + "issue:44987|issue:44991", + "issue:43883|issue:44991", + "issue:45084|issue:45507", + "issue:43089|issue:45987", + "issue:43404|issue:44466" + ], + "prepared_review_unit_hash": "0dd1c295b2e26b55a87c667a5de90da999e0f74e872bf11ee072ecce8fe92f40", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37261, + "estimated_input_tokens": 9316, + "estimated_eval_tokens": 18888 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a set of mostly unrelated closed/open Transformer issues that only share superficial subsystem or version-regression language. I found no convincing duplicate pairs; the soft links are largely false positives.", + "confidence": 0.93, + "canonical_issue_reason": "issue:43611 is the clearest broad regression report in the set: it names the version break, the affected loading path, and a concrete contract change (`base_model_prefix`) with likely wide impact.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the strongest representative issue because it is specific enough to be actionable yet broad enough to capture a common v5 loading regression pattern.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Different failures and code paths: Trainer GPU broadcast of `NoneType` vs Whisper pipeline `return_language` behavior." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory, but one is Qwen3 MoE training inefficiency and the other is Strix Halo mmap OOM; different root causes." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer load regression for a specific model vs a Mistral regex patch crash; same area, but not the same bug." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "`save/from_pretrained` extra_state handling is unrelated to a video-input regression in Qwen multimodal models." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both are device/offload related, but XLNet CPU `arange` placement and Qwen3_5MoE rotary embedding compatibility are distinct issues." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon allocator warmup `TypeError` is unrelated to the `_is_hf_initialized` flag regression." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Loading `cjvt/sleng-bert` and Mistral tokenizer regex patch failures are different model/code-path problems." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "`TOKENIZER_MAPPING_NAMES` model-addition logic and compiled `flex_attention` on torch>=2.9 are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Different models and failures: `cjvt/sleng-bert` load failure vs `physical-intelligence/fast` load failure." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "High perplexity on GPT-OSS is a model/perf issue, while `TokenizersBackend` post-processor updates are a tokenizer runtime behavior bug." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but one is about model loading with `base_model_prefix` and the other about non-persistent buffer serialization." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "These are separate audio bugs: unsupported `center` arg vs `_torch_extract_fbank_features()` behavior." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Mistral image preprocessor dtype mismatch is unrelated to the template-node compilation error." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing `all_tied_weights_keys` in Molmo is unrelated to a model-loading failure for `cjvt/sleng-bert`." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "`trust_remote_code` config-field loss and PagedAttentionCache invalid group type are different subsystems and failures." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer special-token method conflict is unrelated to Qwen3 MoE FP8 config loading." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper, but `batch_decode` ignoring `skip_special_tokens` is a different bug from empty-transcription generation after `align_special_tokens`." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token accounting and Qwen2.5-VL iterable multi-image finetuning failure are unrelated." + }, + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is not the same as `StaticCache.get_seq_length()` returning the wrong type." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Different model-loading regressions affecting different checkpoints and failure modes." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both involve GGUF loading, but one is a general `gguf_file` path break and the other is a Qwen2.5-GGUF v5 regression; not the same concrete bug." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Torch dynamo tracing failure in Mixtral grouped_mm is unrelated to the template-node compile error." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Non-persistent buffer junk serialization and custom model initialization are different regression classes." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Qwen3 MoE FP8 config failure and Qwen3.5 PagedAttentionCache invalid group type are distinct bugs in different code paths." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "`device_map=auto` offload/dequantized loading and Qwen2.5-GGUF loading failure are not the same issue." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Qwen3.5 hidden-states behavior and Qwen2.5-VL rope-index scaling are unrelated model bugs." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer method-name conflict is unrelated to custom model initialization in notebooks." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Same broad area (loading), but different models and errors; not mergeable as one bug fix." + }, + { + "left": "issue:45081", + "right": "issue:45507", + "accept": false, + "reason": "Mistral tokenizer patch crash and GraniteMoEHybrid invalid method are different concrete failures." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Tied-weight wiring in Mistral3 is a model-definition bug, while `lm_head.weight` serialization inconsistency is a separate save/load issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 9, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43540", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43792", + "issue:43819", + "issue:43994", + "issue:44062", + "issue:44079", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44479", + "issue:44534", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44877", + "issue:44987", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45542", + "issue:45663" + ], + "soft_pairs": [ + "issue:43262|issue:43377", + "issue:43994|issue:44610", + "issue:43646|issue:44534", + "issue:43322|issue:43540", + "issue:43645|issue:44534", + "issue:44403|issue:45081", + "issue:43377|issue:43819", + "issue:42915|issue:45084", + "issue:44265|issue:44610", + "issue:44451|issue:45081", + "issue:45216|issue:45357", + "issue:44987|issue:45081", + "issue:44220|issue:44683", + "issue:42915|issue:44291", + "issue:43404|issue:45127", + "issue:43632|issue:44756", + "issue:44062|issue:44987", + "issue:36032|issue:43742", + "issue:44479|issue:45325", + "issue:43296|issue:43531", + "issue:42915|issue:44589", + "issue:40444|issue:45325", + "issue:43531|issue:44877", + "issue:43611|issue:44534", + "issue:36032|issue:41720", + "issue:43425|issue:44403", + "issue:40990|issue:44811", + "issue:41553|issue:43582", + "issue:44079|issue:45663", + "issue:43632|issue:44534", + "issue:42175|issue:45542", + "issue:43792|issue:44589" + ], + "prepared_review_unit_hash": "8bb62c9f48b3130628f2de6138546da2786395e054524b4d4ade1aff3cf9a162", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37221, + "estimated_input_tokens": 9306, + "estimated_eval_tokens": 18868 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a semantic grab-bag of Transformers regressions, with the strongest common thread being v5-era loading/serialization breakages. Most soft pairs are only loosely related by subsystem or model family, not by the same concrete bug.", + "confidence": 0.42, + "canonical_issue_reason": "issue:43611 is the broadest representative of the main theme in this cluster: Transformers v5 loading regressions. Its title is generic enough to cover several nearby load/init failures, without being tied to one narrow model.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best single issue to represent the cluster because it captures the shared \u2018v5 breaks model loading\u2019 pattern more cleanly than the model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Both are audio-related, but one is a chat-template sampling-rate default and the other is a batching/padding-mask correctness bug in MIMI." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different models and different failures: SigLIP2 bad outputs vs OmDet-Turbo processor/model input-size mismatch." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization breakage is not the same bug as non-persistent buffers being filled with junk." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Both are multimodal loading/input errors, but Llava Next segfault and Qwen3OmniMoe video ValueError are distinct code paths." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook/custom-model init failure is unrelated to the buffer-initialization corruption described in 44534." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Generic loading noise is not the same underlying problem as a tokenizer regex patch crash." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "Different audio model families and different bugs: padding-mask batching vs DAC latent/forward mismatch." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3Moe FP8 config failure is unrelated to the template-node compilation error." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export failure with torch_compilable_check is a different issue from OmDet-Turbo processor input sizing." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "A model load failure for ScandiBERT is not the same as the Mistral tokenizer regex patch crash." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": false, + "reason": "These are related Qwen3.5 save_pretrained regressions, but 45357 is a narrower visual-encoder-key follow-up rather than the same concrete bug as 45216." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Different failure modes: loading a specific model repo vs crashing inside Mistral regex patching." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Feature-extraction audio issue and compiled flex_attention torch-version incompatibility are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Different model/setup and different root cause: Qwen3Moe FP8 config vs init_empty_weights unexpected argument." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both touch tied weights, but one is a missing lm_head tie in Mistral3 and the other is LoRA merge collapse after vocab extension." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized flag breakage is unrelated to the mmap/OOM issue on Strix Halo." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "Duplicate AddedToken special-arg handling is not the same as loading physical-intelligence/fast failing." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "T5 tokenizer add_special_tokens conflict and MobileLLM key error are different loading bugs." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both concern Qwen vision/video behavior, but the broad video-input regression is not the same as the still-image temporal position_id scaling bug." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL loading in vLLM and Qwen3-MoE sliding_window are unrelated failures." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Qwen3Moe FP8 config failure is not the same as the missing Float8 storage type issue." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "IterableDataset multi-image finetuning failure is different from the Qwen2.5-VL rope-index scaling regression." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE and strict-config loading for granite_speech are distinct problems." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Generic model-loading breakage is not the same bug as junk-filled non-persistent buffers." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer loading conflict and Qwen3 auto-device-map CUDA assert are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch version incompatibility and loading noise are not the same concrete issue." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "High perplexity on gpt-oss is unrelated to Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error messaging for Voxtral is unrelated to the Apple Silicon warmup TypeError." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment and Gemma4 shared_kv_states/FSDP2 are different bugs." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "_is_hf_initialized regression and non-persistent buffer corruption are distinct v5 breakages." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Pip extras/backend dependency omission and tensorboard-without-TensorFlow backend errors are related only loosely, not the same bug." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper model runtime failure and missing Float8 storage object 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": 1, + "component_count": 17, + "review_unit_index": 10, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:33666", + "issue:35707", + "issue:40444", + "issue:41720", + "issue:42175", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43381", + "issue:43421", + "issue:43454", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43646", + "issue:43749", + "issue:43818", + "issue:43856", + "issue:43994", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44466", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44829", + "issue:44898", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45812", + "issue:45834", + "issue:45923" + ], + "soft_pairs": [ + "issue:43421|issue:44568", + "issue:43818|issue:45357", + "issue:44683|issue:45020", + "issue:44403|issue:44991", + "issue:44462|issue:45812", + "issue:33666|issue:40444", + "issue:43482|issue:45538", + "issue:43317|issue:43856", + "issue:43381|issue:45923", + "issue:44829|issue:45479", + "issue:35707|issue:40444", + "issue:44291|issue:44589", + "issue:44079|issue:44534", + "issue:43482|issue:43525", + "issue:43377|issue:45491", + "issue:43749|issue:44079", + "issue:40444|issue:45381", + "issue:43531|issue:44291", + "issue:41720|issue:45081", + "issue:43644|issue:44079", + "issue:44265|issue:45072", + "issue:45325|issue:45381", + "issue:42175|issue:43296", + "issue:43632|issue:45072", + "issue:43994|issue:44898", + "issue:43611|issue:43646", + "issue:43454|issue:44466", + "issue:45325|issue:45834" + ], + "prepared_review_unit_hash": "c21410207077f01a4dd113af1719d7eafb9936856fbcedcda2f7a5482e66726f", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35748, + "estimated_input_tokens": 8937, + "estimated_eval_tokens": 18130 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated bug reports spanning different models, loading paths, and regressions. I found no high-confidence duplicate pair among the soft edges, so the cluster should not be merged as a duplicate set.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45020 is the best umbrella anchor: it is broad, well-documented, and represents a major transformer-v5 regression class rather than a narrow model-specific symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the most representative and actionable issue in this mixed cluster, with the broadest scope and strongest discussion trail.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Both involve tokenization behavior, but one is runtime post-processor refresh and the other is add_special_tokens/BOS-EOS behavior for a specific tokenizer; not the same bug." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Different model families and failure modes: Video-LLaVA tower architecture vs Qwen3.5 save_pretrained key serialization." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Torch 2.9 flex_attention compilation failure is a distinct backend regression from remote_code model loading breakage." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Unnecessary loading noise and tokenizer-loading failure are separate symptoms in different code paths." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both are AutoTokenizer issues, but one ignores tokenizer.json while the other returns wrong Granite token IDs; not clearly the same defect." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Different Qwen2-VL/Qwen2.5-VL training workflows and distinct multi-image dataloader failure." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading under v5 and CLIPTokenizer model_max_length behavior are unrelated tokenizer/model-loading bugs." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Device-map offload load failure and Qwen3 MoE training memory usage are different problems in different phases." + }, + { + "left": "issue:43381", + "right": "issue:45923", + "accept": false, + "reason": "Eval-mode gradient checkpointing restriction is not the same as a missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Both end in degenerate training, but one is flash_attention_3-specific and the other is a num_labels=1 loss formulation bug." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image finetuning failure." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is a different initialization path from Float8 storage resolution failures." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment and non-persistent buffer junk are separate internal state-management issues." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "GGUF loading regression and missing pad_token_id on Llama4Config are not the same underlying bug." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Batch-vs-single MIMI padding-mask mismatch and Gemma3 NaNs from all-padding windows are different model-specific attention/padding bugs." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP CPU RAM-efficient loading and ModelOutput key handling are unrelated subsystems." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Multi-image prompt finetuning failure is distinct from Qwen2.5-VL video vision_position_ids regression." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights argument handling are different regressions." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Auto device mapping cudaErrorAssert on A800 is unrelated to Mistral tokenizer regex patch crashes." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk and ModelOutput key assignment bugs are different internal behaviors." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export with torch_compilable_check and bfloat16 dtype mismatches are not the same code-path problem." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL position-id regressions, but one is still-image temporal scaling and the other is video vision_position_ids; related, but not confidently the same bug." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Missing TensorFlow backend from pip extras and PaddleOCR-VL load failure are unrelated packaging/loading issues." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "_is_hf_initialized breakage in v5 is unrelated to dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and Perceiver resize/interpolation failure are different model-specific vision issues." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both mention transformers v5 breakage, but base_model_prefix loading and custom model initialization are separate failures." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "AyaVision weight tying failure and lm_head.weight serialization inconsistency are related only at a high level; not the same bug." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Qwen2.5-VL temporal position-id scaling and Kosmos2.5 OCR index error are different model behaviors." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 11, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43701", + "issue:43746", + "issue:43792", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43957", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44479", + "issue:44488", + "issue:44568", + "issue:44610", + "issue:44617", + "issue:44877", + "issue:44898", + "issue:44991", + "issue:45072", + "issue:45325", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45920", + "issue:45923" + ], + "soft_pairs": [ + "issue:43792|issue:43957", + "issue:42915|issue:43482", + "issue:43296|issue:45800", + "issue:44387|issue:44617", + "issue:43701|issue:45325", + "issue:44479|issue:45823", + "issue:43881|issue:44488", + "issue:44291|issue:44877", + "issue:43606|issue:44265", + "issue:43262|issue:43746", + "issue:40990|issue:45584", + "issue:44568|issue:45920", + "issue:34634|issue:35707", + "issue:43873|issue:45701", + "issue:44186|issue:44265", + "issue:35707|issue:41720", + "issue:43606|issue:43819", + "issue:41720|issue:45823", + "issue:43454|issue:43550", + "issue:43377|issue:44610", + "issue:43317|issue:43873", + "issue:39692|issue:40444", + "issue:43572|issue:45759", + "issue:43377|issue:44898", + "issue:43257|issue:45923", + "issue:43454|issue:45072", + "issue:43526|issue:43883", + "issue:40990|issue:42947", + "issue:43881|issue:44991" + ], + "prepared_review_unit_hash": "db777973969792720703289d080eb2c5367d361d79033a059bfe131a5a350879", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "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": "The cluster is heterogeneous: it contains many unrelated issue reports across model loading, tokenization, quantization, audio, vision, and device-mapping paths. None of the soft pairs look like the same underlying bug/change, so they should all remain separate.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue: the items span distinct subsystems and failure modes rather than one duplicate family.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue candidate; none is a clear superset or central representative of the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Different symptoms and scope: Whisper runtime failure vs a general torch.device(\"meta\") loading regression affecting multiple models." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Unrelated bugs: FineGrainedFP8Config failure for Qwen3Moe vs GGUF loading failure for Qwen2.5 under transformers v5." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "Different version stacks and failure modes: PaddleOCR-VL/vLLM load issue vs torch 2.4.1 and transformers 5.8.0 incompatibility." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Both mention OOM, but one is an int4 quantization memory regression and the other is a model-specific Sam3Video CUDA OOM." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Different code paths: checkpoint resume key mismatch vs Qwen2.5-VL rope/position-id scaling bug." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Different models and issues: Qwen video-input regression vs Gemma4 PLE device mismatch during forward." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Separate model-loading failures for different checkpoints; no shared concrete bug is evident." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "One is an init_empty_weights argument regression; the other is strict config validation blocking granite_speech config loading." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "Different subsystems: CPU offload device mismatch vs torch.export failure around torch_compilable_check." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sampling-rate default bug vs GraniteSpeech PEFT checkpoint loading issue are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "Different model/workflow failures: GPT-OSS perplexity anomaly vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:44568", + "right": "issue:45920", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different tokenizers and likely different root causes." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "Unrelated: Bark voice_preset does not work vs progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Different regressions: quantization/offloading behavior vs version-dependent tokenization changes." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer crash on NER/padding vs export failure with torch_compilable_check are different bugs." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "No common underlying bug: generation cache handling vs Qwen3 device-mapping cudaErrorAssert." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to DAC.from_latents not matching forward pass." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Different models and failure causes: Qwen3 auto device mapping assert vs Gemma4 PLE device mismatch." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "AyaVision lm_head tying bug is unrelated to Bamba SDPA/torch.compile failure." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Different modalities and root causes: MIMI batching/padding-mask bug vs OmDet-Turbo processor size mismatch." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both involve offloading/quantization, but one is dequantized-model loading with device_map=auto and the other is a broader offloading complaint." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Documentation/model-processor mismatch and quantization example errors are unrelated to Qwen2.5-VL multi-image finetuning failure." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Different config regressions: missing pad_token_idx in StableLmConfig vs not unwrapping text_config for composite multimodal configs." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Different image/audio preprocessing bugs: MIMI padding-mask mismatch vs Perceiver non-default resolution failure." + }, + { + "left": "issue:43257", + "right": "issue:45923", + "accept": false, + "reason": "Distinct issues: Qwen3 MOE weight conversion under accelerate/deepspeed vs missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Different bugs in different models: weight tying corruption vs dtype mismatch during bfloat16 inference." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "Unrelated issues: BeitImageProcessorFast reduce_labels bug vs Molmo missing all_tied_weights_keys attribute." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "Different problem domains: perplexity regression on GPT-OSS vs gradient checkpointing ineffectiveness with PEFT LoRA." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer/model loading failures for different models; no evidence of a shared defect." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 12, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43296", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43404", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43749", + "issue:43873", + "issue:43881", + "issue:44008", + "issue:44186", + "issue:44387", + "issue:44423", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44610", + "issue:44671", + "issue:44743", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45161", + "issue:45357", + "issue:45406", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45823" + ], + "soft_pairs": [ + "issue:44466|issue:45357", + "issue:43749|issue:44534", + "issue:43454|issue:43720", + "issue:41720|issue:43322", + "issue:43296|issue:44877", + "issue:41720|issue:44977", + "issue:44008|issue:45823", + "issue:42617|issue:42915", + "issue:40990|issue:45701", + "issue:43404|issue:45357", + "issue:45632|issue:45684", + "issue:44186|issue:45072", + "issue:44423|issue:45406", + "issue:43577|issue:43708", + "issue:44387|issue:45704", + "issue:44877|issue:44991", + "issue:43873|issue:44756", + "issue:36331|issue:42617", + "issue:36331|issue:42915", + "issue:43550|issue:43720", + "issue:43450|issue:45701", + "issue:44610|issue:44898", + "issue:44186|issue:44610", + "issue:44479|issue:44918", + "issue:41720|issue:42617", + "issue:43550|issue:43606", + "issue:42915|issue:43317", + "issue:43316|issue:44913", + "issue:43295|issue:45701", + "issue:43526|issue:43881", + "issue:44671|issue:44743", + "issue:41720|issue:45161" + ], + "prepared_review_unit_hash": "055bb3b15fe5c63f4e0d8b5ff9018299da87fcbac732b251cd536d1a89a09aa1", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37368, + "estimated_input_tokens": 9342, + "estimated_eval_tokens": 18940 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are a mixed set of unrelated model-, tokenizer-, loading-, and trainer-specific bugs. None of the soft pairs look like the same underlying defect closely enough to merge, so there is no single canonical issue for this cluster.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both involve saving/serialization, but the bugs are different: tied lm_head serialization vs incorrect visual encoder keys for Qwen3.5." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "Both mention v5/loading regressions, but one is FSDP CPU-efficient loading and the other is non-persistent buffer initialization; different fixes." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Different models and code paths: AyaVision lm_head tying vs BitNet packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Separate failures on different models: CUDA assert with auto device mapping vs segfault loading Llava Next." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "One is a PaddleOCR-VL/vLLM load failure, the other is strict config blocking granite_speech; only loosely related to loading." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Both are Qwen-related, but one is device-mapping CUDA assert and the other is flash-attention generation behavior." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma-family, but the concrete bugs differ: variable name collision in Gemma3n vs device mismatch in Gemma4 PLE." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "Unrelated: a 3d_parallel.py runtime issue versus a FineGrainedFP8Config failure on Qwen3Moe." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Perplexity on GPT-OSS-20B is not the same defect as a tokenization behavior change across versions." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Different bugs: Mistral3 lm_head tying vs Qwen3.5 visual encoder key serialization." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Both are save/load path issues, but one is cache path collision and the other is file permission propagation; not the same bug." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer crash on NER/batched padding is unrelated to dtype mismatches in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Both crash in serve, but the failing attributes and models differ: str.to on multimodal inputs vs Gemma4Processor._tokenizer." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "One is a dtype loading bug in Blip2; the other is a Trainer max_steps resume calculation bug." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Different regression classes: int4 CUDA memory growth vs apex.FusedRMSNorm memory leak in T5." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Both are load failures, but config strictness and tokenizer loading are different root causes." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both touch memory/offload, but one is quantization offloading behavior and the other is Strix Halo mmap OOM." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "CustomTrainer.compute_loss signature break is unrelated to a 3d_parallel.py execution failure." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Different failures: Trainer API mismatch versus Qwen3Moe FP8 loading." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile with SDPA on Bamba is a different code path from accelerate loading of packed BitNet weights." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Incorrect batched video processor shapes are unrelated to version-dependent tokenization changes." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both are vision preprocessing issues, but one is wrong processor output size and the other is non-default resolution handling in Perceiver." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer crash on NER/padding is unrelated to OmDet-Turbo image size mismatch." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Both involve Qwen3.5, but one is a video-input regression and the other is input-embedding unpacking in TRL SFT training." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert is unrelated to the 3d_parallel.py failure." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "torch.compile/SDPA failure is not the same as a CPU-offload device mismatch on suno/bark-small." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Different loading problems: FineGrainedFP8Config failure vs dequantized model load failure with device_map=auto." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Config API discrepancy and GPTNeoX rotary_pct reload regression are different configuration bugs." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "A processor.tokenizer/image-passing regression is not the same as a broad tokenization change across versions." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "BEiT Fast label reduction bug is unrelated to glm-4v-9b loading failure." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM prediction corruption is unrelated to Qwen3.5 recurrent-state reset behavior." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both mention Qwen/GPT-OSS family problems, but one is CUDA assert with auto mapping and the other is tensor parallelism not working for GPT-OSS MoE." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 13, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:30064", + "issue:33357", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:41720", + "issue:42490", + "issue:42617", + "issue:42915", + "issue:43322", + "issue:43329", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43873", + "issue:43927", + "issue:44186", + "issue:44361", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44625", + "issue:44898", + "issue:44991", + "issue:45059", + "issue:45072", + "issue:45081", + "issue:45357", + "issue:45381", + "issue:45406", + "issue:45464", + "issue:45479", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45812" + ], + "soft_pairs": [ + "issue:45081|issue:45812", + "issue:43531|issue:43572", + "issue:43540|issue:43782", + "issue:36010|issue:42617", + "issue:43421|issue:45812", + "issue:44186|issue:44361", + "issue:42915|issue:43322", + "issue:43388|issue:45059", + "issue:45406|issue:45464", + "issue:33357|issue:35707", + "issue:43421|issue:45701", + "issue:30064|issue:34634", + "issue:44492|issue:44509", + "issue:41720|issue:43746", + "issue:43606|issue:43720", + "issue:43550|issue:43653", + "issue:43873|issue:45704", + "issue:44514|issue:44545", + "issue:43606|issue:43653", + "issue:43531|issue:45759", + "issue:42490|issue:43329", + "issue:34634|issue:41720", + "issue:34567|issue:35707", + "issue:44625|issue:45479", + "issue:43421|issue:43927", + "issue:44368|issue:45357", + "issue:43782|issue:45381", + "issue:44451|issue:44991", + "issue:44898|issue:45072" + ], + "prepared_review_unit_hash": "0cd57974f2896455cf38930e2c6d37761d7d992c22e38e53d9b9e343e170dc44", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36654, + "estimated_input_tokens": 9164, + "estimated_eval_tokens": 18584 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are clearly unrelated despite surface similarity. Only issue 44514 and issue 44545 look like true duplicates of the same Qwen2_5_VLProcessor batched-padding crash.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 44545 is the best canonical issue in the set because it is part of the only exact duplicate pair, has the same concrete repro as 44514, and carries slightly more discussion/inbound reference signal.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44545 is the strongest issue to keep as representative: it names the exact failing code path, matches 44514 nearly verbatim, and appears to be the more established report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Different bugs in different tokenizer paths: Mistral regex patch crash vs Granite token-id regression." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Unrelated: Qwen3-MoE sliding-window behavior vs StableLm config missing pad_token_idx." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Different model families and failures: Qwen3OmniMoe video ValueError vs Qwen3VL weight_only load error." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to a script execution problem for 3d_parallel.py." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Runtime special-token post-processor update bug is not the same as Granite token IDs being wrong." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizers and failure modes: LayoutLMv2 batching crash vs MLuke AttributeError." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Llava Next segfault are separate loading/runtime issues." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Metrics label dropping and SAM3 text/bbox weirdness are different subsystems and symptoms." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer is unrelated to Qwen3.5 streaming chat/completions failure." + }, + { + "left": "issue:33357", + "right": "issue:35707", + "accept": false, + "reason": "MacOS bus error on CLIP model loading is not the same as generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "A runtime special-token update bug is not the same as a broad tokenization version-change regression." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Void segmentation maps and Bark voice_preset are unrelated model/data-path bugs." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A docs typo is not the same as stale pipeline-task documentation after v5 removal." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3 auto device-mapping cuda assert and GraniteSpeech PEFT local-load failure are different code paths." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "CPU offload device mismatch and BitNet packed-weight unpacking are separate loading/offload defects." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba is unrelated to BigBirdTokenizer special-token registration." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization/offloading behavior and T5 apex FusedRMSNorm memory leak are not the same bug." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Near-verbatim duplicate: both report Qwen2_5_VLProcessor.apply_chat_template crashing on batched input with padding=False." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Device-mismatch CPU offload bug is unrelated to BigBirdTokenizer mask-token registration." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE is not the same as AutoModelForCausalLM.from_config not unwrapping text_config." + }, + { + "left": "issue:42490", + "right": "issue:43329", + "accept": false, + "reason": "Trailing-slash local-model import warning and a multimodal video-token helper bug are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice_preset failure and Qwen3 device-mapping cudaErrorAssert are different problems." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counter not updating is unrelated to progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and degenerate zero-loss classification are different sequence-classification issues." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Special-token post-processor updating and DiaConfig losing custom token IDs after save/load are distinct bugs." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "tie_word_embeddings warning in Qwen3.5 LoRA training is unrelated to incorrect visual-encoder keys in save_pretrained." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Qwen3VL weight_only loading error is not the same as Qwen2.5-VL video vision_position_ids being wrong." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Failed model loading for ScandiBERT and tokenizer loading regression for est-roberta are different model-specific issues." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver image-classification interpolation bug and dtype mismatches in SwitchTransformers/TimmWrapperModel are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: issue 44514 and 44545 are near-verbatim duplicates with matching titles and compatible repros, and the inbound-reference counts support choosing 44545 as canonical. The soft-edge rejections stay conservative and rely on clearly different titles/failure modes. No PR-pair mergeability concerns apply here." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 14, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:39692", + "issue:40444", + "issue:41720", + "issue:42886", + "issue:42915", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43596", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43819", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44451", + "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:45479", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45859", + "issue:45907", + "issue:45923" + ], + "soft_pairs": [ + "issue:44077|issue:44625", + "issue:44987|issue:45042", + "issue:43531|issue:44589", + "issue:45759|issue:45859", + "issue:44062|issue:44451", + "issue:39692|issue:44610", + "issue:45704|issue:45923", + "issue:44918|issue:44936", + "issue:43421|issue:43653", + "issue:45588|issue:45759", + "issue:45663|issue:45923", + "issue:42886|issue:44843", + "issue:43381|issue:43844", + "issue:43421|issue:44186", + "issue:43994|issue:44671", + "issue:43525|issue:43531", + "issue:45704|issue:45859", + "issue:45081|issue:45356", + "issue:41720|issue:45704", + "issue:43596|issue:44220", + "issue:39692|issue:43873", + "issue:45356|issue:45907", + "issue:43746|issue:43873", + "issue:40444|issue:43746", + "issue:42915|issue:43746", + "issue:43540|issue:44008", + "issue:44220|issue:44661", + "issue:43720|issue:43819", + "issue:30064|issue:36010", + "issue:45183|issue:45479" + ], + "prepared_review_unit_hash": "6ed42d43a328c893dc5dbd2b5d25c483d47c9ec7bc705ec92735a4db84f5cebc", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36483, + "estimated_input_tokens": 9121, + "estimated_eval_tokens": 18498 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a single duplicate group: the items span many unrelated bugs/features across tokenizers, multimodal models, training, quantization, and offloading. None of the soft-similarity pairs are close enough to merge as the same underlying change or bug.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Different problems: one is about PatchTSMixer post_init being optional, the other about Qwen3.5 num_labels propagation." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Both involve loading/models, but the failures are different: one is a loading regression for a specific repo, the other is PIL image processors incorrectly requiring torchvision." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Separate code paths: Qwen3-MoE sliding-window logic vs a storage-class lookup error when loading float8 tensors." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Related to Qwen 3.5/3.6 multimodal configs, but one is about from_config not unwrapping text_config and the other is CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "Both are tokenizer-related, but one is an AddedToken constructor error and the other is a model-loading failure for a specific checkpoint." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both touch vision models, but one is a docs/example mismatch and quantization issue; the other is an OmDet-Turbo processor/model input-size mismatch." + }, + { + "left": "issue:45704", + "right": "issue:45923", + "accept": false, + "reason": "Unrelated model internals: apex FusedRMSNorm memory leak in T5 vs missing supports_gradient_checkpointing on a trust_remote_code model." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different training failures: Qwen3.5 embedding unpacking with TRL SFT trainer vs trainer.evaluate failing after train." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both concern tokenizers, but one is runtime special-token/post-processor updates; the other is BigBirdTokenizer special-token registration for mask decoding." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention crash on sink-less models is unrelated to Qwen multimodal config handling." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "Different model families and failures: Gemma-4 FSDP2 shared_kv_states bug vs Nemotron-3-Nano-Omni missing gradient-checkpointing support." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": false, + "reason": "Both involve offline/cache behavior, but one is tokenizer cache loading on 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": "Training-mode/eval-mode checkpointing issue is not the same as the ZeRO-3 gradient growth bug." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Tokenizer post-processor updates are unrelated to LayoutLMv2Tokenizer crashes on NER inputs and batched padding/truncation." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Both affect model outputs, but one is a SigLIP2 loading/pipeline issue and the other is a CamemBERT masked-LM regression in v5." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Different model/config bugs: missing pad_token_id on Llama4Config vs sliding_window behavior in Qwen3-MoE." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "Apex/T5 RMSNorm memory leak is not the same as Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both mention fix_mistral_regex, but one is a crash in the regex patch path and the other is a Kimi-K2.5 codec regression plus misleading warning." + }, + { + "left": "issue:41720", + "right": "issue:45704", + "accept": false, + "reason": "Qwen3 CUDA assert with auto device mapping is a different failure mode from a T5 RMSNorm memory leak." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Different subsystems: deepspeed zero3 init with BertModel vs _torch_extract_fbank_features audio extraction." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "Docs/example SigLIP2 errors are unrelated to the broader offloading-with-quantization behavior issue." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Both touch HF Hub/tokenizer utilities, but one is a tokenizer codec/regression issue and the other is list_repo_files not forwarding revision." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "PEFT local checkpoint loading for GraniteSpeech is not the same as offloading misbehavior under quantization." + }, + { + "left": "issue:40444", + "right": "issue:43746", + "accept": false, + "reason": "Multi-image IterableDataset finetuning failure is unrelated to PEFT-adapter local checkpoint loading." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure and GraniteSpeech PEFT loading failure are distinct code paths." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Both are multimodal, but one is a Qwen3OmniMoe video-processing ValueError and the other is a Gemma 3n variable-name collision causing an AttributeError." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction bug is unrelated to add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Both are BitNet/DAC model issues, but one is about unpacking packed weights during accelerate loading and the other is DAC.from_latents not matching forward due to missing STE." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Completely different areas: image processor void segmentation maps vs a transformers.GenerationMixin import error." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "General input validation XOR messaging bug is not the same as the single-label-classification num_labels=1 zero-loss issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 15, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:30064", + "issue:36331", + "issue:39692", + "issue:43295", + "issue:43322", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43618", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43825", + "issue:43950", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44448", + "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", + "issue:45987" + ], + "soft_pairs": [ + "issue:43618|issue:43697", + "issue:43653|issue:43720", + "issue:43335|issue:43756", + "issue:43295|issue:45834", + "issue:43716|issue:44008", + "issue:43550|issue:45072", + "issue:43550|issue:43819", + "issue:44062|issue:44488", + "issue:43322|issue:45685", + "issue:43950|issue:45987", + "issue:44186|issue:44898", + "issue:44843|issue:45081", + "issue:43531|issue:43643", + "issue:43653|issue:43819", + "issue:43643|issue:44877", + "issue:43421|issue:44811", + "issue:43577|issue:43818", + "issue:43540|issue:45381", + "issue:43782|issue:44977", + "issue:44448|issue:44671", + "issue:45584|issue:45834", + "issue:39692|issue:45834", + "issue:44561|issue:45020", + "issue:44485|issue:44509", + "issue:44821|issue:45084", + "issue:30064|issue:36331", + "issue:43825|issue:43994" + ], + "prepared_review_unit_hash": "251086b3a0075b1b9a06bbe8634c7ba1b0366ba6e895b1da7d629f0346d08e91", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36057, + "estimated_input_tokens": 9015, + "estimated_eval_tokens": 18286 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated Transformers issues. The high-scoring soft pairs share broad subsystems at most, but not the same concrete bug or code path, so none should be deduplicated or merged as one change.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the broadest and best-described umbrella report in the set, but it is still too generic to act as a true duplicate canonical for the other issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Different failures in different models: CLIP attentions assignment vs RT-DETR output drift." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token registration bug vs BitNet accelerate loading/unpacking bug; unrelated code paths." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "One is a SwitchTransformers sparse-layer config bug; the other is a Smollm3 RoPE-layer mismatch." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Both concern tokenizer/processor-style inputs, but the root causes are different: processor.tokenizer regression vs long OCR index error." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Separate model families and distinct bugs: dtype mismatch in Mistral vs variable name collision in Gemma3n." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Both are runtime/inference regressions, but they affect different models and code paths (SDPA compile vs dtype mismatch)." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Completely different models and bugs: torch.compile+SDPA failure vs DAC forward/from_latents mismatch." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken kwarg collision is a tokenizer API bug; cjvt/sleng-bert load failure is a model-loading issue." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Both are model/runtime crashes, but one is Llava Next loading segfault and the other is an MPS histogram dtype limitation." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Non-persistent buffer corruption during from_pretrained is unrelated to StaticCache.get_seq_length returning the wrong shape." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer/NER padding crash vs Perceiver image classification failure; no shared underlying bug." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both involve Mistral tokenizer patching, but one is offline model_info access and the other is a backend_tokenizer AttributeError; different root causes." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE is unrelated to trust_remote_code config-field loss." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "Tokenizer special-token handling and DAC latent reconstruction are unrelated bugs." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both touch config loading, but one is trust_remote_code field loss and the other is strict config rejection for granite_speech." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime special-token/post-processor update bug vs Whisper batch_decode skip_special_tokens handling; different behavior." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing are distinct issues." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Different Qwen multimodal models and different video-input bugs." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3VL weight_only loading error is unrelated to Qwen3.5 flash-attention generation behavior." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Both are version-regression reports, but they concern different models and outputs." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription failure and Kosmos2.5 long-OCR index error are unrelated edge cases." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "Documentation/example errors for SigLIP2 are not the same bug as Kosmos2.5 OCR input indexing." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "44561 is one specific remote_code regression cause; 45020 is a broader umbrella complaint, not the same underlying bug." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to removed pipeline-task documentation." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and template-node compile errors are different subsystems and failure modes." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "ImageProcessor segmentation-map handling and CustomTrainer compute_loss signature mismatch are unrelated." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "Pipeline task messaging and SigLIP2 nonsensical outputs are different issues with no common 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": 1, + "component_count": 17, + "review_unit_index": 16, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:34634", + "issue:36010", + "issue:36331", + "issue:41720", + "issue:42175", + "issue:43262", + "issue:43329", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43644", + "issue:43650", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:44060", + "issue:44186", + "issue:44291", + "issue:44368", + "issue:44442", + "issue:44479", + "issue:44554", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44857", + "issue:44936", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45406", + "issue:45459", + "issue:45538", + "issue:45600", + "issue:45701", + "issue:45803", + "issue:45834" + ], + "soft_pairs": [ + "issue:41720|issue:44991", + "issue:43644|issue:43749", + "issue:44186|issue:44442", + "issue:44479|issue:45834", + "issue:43606|issue:45072", + "issue:44805|issue:44936", + "issue:43825|issue:43827", + "issue:43577|issue:43582", + "issue:34634|issue:36010", + "issue:44671|issue:45701", + "issue:44610|issue:45072", + "issue:43782|issue:45325", + "issue:43720|issue:45072", + "issue:42175|issue:45081", + "issue:45081|issue:45406", + "issue:43749|issue:44291", + "issue:43650|issue:43906", + "issue:43582|issue:44857", + "issue:44060|issue:44368", + "issue:43262|issue:43819", + "issue:43526|issue:43697", + "issue:43526|issue:44554", + "issue:34634|issue:36331", + "issue:45459|issue:45803", + "issue:45084|issue:45538", + "issue:43742|issue:45020", + "issue:43329|issue:45600" + ], + "prepared_review_unit_hash": "b822be1294093627d358262f328fbe3045fb09937c3f4db57f9a94d7ee011d34", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35509, + "estimated_input_tokens": 8878, + "estimated_eval_tokens": 18012 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most candidates are broad-similarity false positives (same subsystem or release, but different concrete bugs). Only the Qwen tied-weights warning reports look like the same underlying issue.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44060 is the clearest, most concrete report of the Qwen tied-weights warning bug; issue:44368 reads like a downstream duplicate/symptom of the same warning path.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44060 best captures the root bug with a specific mis-tie (`embed_tokens.weight` vs `linear_attn.dt_bias`) and broad enough scope to serve as the canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Different failures: Qwen3 auto device-map CUDA assert vs tokenizer import/load failure for est-roberta." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both concern v5 loading behavior, but one is non-persistent buffer corruption and the other is FSDP CPU RAM efficient loading; not the same bug." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer problems, but one is LayoutLMv2 NER/padding crashes and the other is AutoTokenizer loading FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Both are multimodal input bugs, but on different models and code paths (video regression vs OCR long-input index error)." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Device-mismatch CPU-offload bug for Bark vs bfloat16 dtype mismatch in different models." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Both are runtime errors, but one is a mask/tensor shape mismatch and the other is train-then-evaluate behavior." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Related to v5 pipeline removals, but one is an error message bug and the other is outdated docs; not the same concrete fix." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Blip2 dtype persistence vs Apple Silicon caching allocator TypeError are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset issue is unrelated to the GenerationMixin import error." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "CamemBERT masked-LM regression and generic tokenization changes are not the same bug." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "OmDet-Turbo image-size mismatch vs dtype mismatch in other models." + }, + { + "left": "issue:43782", + "right": "issue:45325", + "accept": false, + "reason": "Qwen VL load-time `weight_only` error vs still-image rope-index scaling bug are different paths." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is unrelated to dtype mismatch." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Missing TensorFlow backend in install extras is unrelated to tokenizer regex patch crash." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both are tokenizer/processor crashes, but one is a Mistral regex patch bug and the other is a Gemma4Processor missing attribute." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both touch model loading, but one is FSDP CPU RAM efficient loading and the other is init_empty_weights argument mismatch." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "The titles are unrelated; one is a placeholder issue and the other is a reproduction of a different issue." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon warmup TypeError and CUDA float16 AMP crash are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": true, + "reason": "Same underlying tied-weights warning bug in Qwen3/Qwen3.5-family models; both report the incorrect warning path and should be fixed together." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio processor sampling-rate default bug vs DAC latent/forward mismatch are different issues." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Beit reduce_labels bug and RTDetrV2 output drift are different model-specific regressions." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and MPS attention correctness are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice preset failure is unrelated to CustomTrainer.compute_loss signature breakage." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both involve exception handling, but in different code paths and with different root causes; too broad to merge." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Template compilation TypeError and CLIPTokenizer max_length bug are unrelated." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "Specific MobileLLM key error is not the same as broad remote_code breakage." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Multimodal token counting bug and removed auto_mappings config references are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. Most soft-edge rejections are conservative and the reasons track distinct titles/subsystems. The single accepted Qwen pair is a plausible match based on the shared tied-weights warning theme. No clear overstatement beyond the available packet evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 17, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:34567", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:42490", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43454", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43638", + "issue:43643", + "issue:43645", + "issue:43653", + "issue:43696", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44479", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45042", + "issue:45356", + "issue:45357", + "issue:45488", + "issue:45701", + "issue:45759", + "issue:45859" + ], + "soft_pairs": [ + "issue:43653|issue:44912", + "issue:43638|issue:44936", + "issue:43452|issue:44991", + "issue:43746|issue:44811", + "issue:44589|issue:45042", + "issue:38175|issue:44610", + "issue:43854|issue:44977", + "issue:43819|issue:43927", + "issue:36010|issue:43645", + "issue:39692|issue:44912", + "issue:43257|issue:43329", + "issue:43550|issue:44912", + "issue:43720|issue:44610", + "issue:43257|issue:43696", + "issue:43454|issue:43577", + "issue:43531|issue:45042", + "issue:43329|issue:44479", + "issue:43262|issue:44811", + "issue:42490|issue:43257", + "issue:36010|issue:36331", + "issue:44568|issue:45356", + "issue:43749|issue:44756", + "issue:43643|issue:45759", + "issue:34567|issue:40990", + "issue:43329|issue:43450", + "issue:44568|issue:45488", + "issue:43257|issue:43931", + "issue:43606|issue:45859", + "issue:44849|issue:45701", + "issue:43697|issue:45357" + ], + "prepared_review_unit_hash": "329319f65b49f5f036ae111771bbc3968d1117f6cc937d7c63ce6bc5d8536037", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36996, + "estimated_input_tokens": 9249, + "estimated_eval_tokens": 18754 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly unrelated and grouped by surface similarity. The 43329\u219444479 pair is only weakly related through multimodal/video vocabulary; the packet does not establish they are the same underlying bug or a mergeable shared fix.", + "confidence": 0.69, + "canonical_issue_reason": "issue:44479 is the best canonical issue because it captures the broader user-facing video-input regression across multiple Qwen VL variants. issue:43329 is narrower and may be adjacent, but the packet does not prove it is the same defect.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the strongest representative due to broader impact and clearer regression framing; issue:43329 is more specific and less well-supported as the root of the broader behavior.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Different bugs: BigBird special-token registration vs MXFP4 quantization loading fallback." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Both are trainer failures, but the concrete breakages differ: ZeRO-3 indexing vs evaluate-after-train behavior." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both involve loading/tokenizer paths, but they point to different models and code paths." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "PEFT local-checkpoint loading and Whisper batch_decode special-token handling are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Float8 storage lookup error is unrelated to PIL backend torchvision dependency checks." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Different model families and failure modes: zero probabilities vs image-size mismatch." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Generic model-load test failure vs flash-attention generation bug; no shared code-path evidence." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent reconstruction mismatch and DiaConfig save/load token-ID loss are distinct bugs." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import error and Jupyter custom-model initialization breakage are different regressions." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Documentation example errors are not the same bug as MXFP4 quantization loading fallback." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MoE weight conversion during accelerate+deepspeed loading is unrelated to a multimodal video-token helper bug." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "torch.compile SDPA failure on Bamba is unrelated to git-oss quantization fallback behavior." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Packed-weight unpacking during loading and processor image-size mismatch are different issues." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "One is a loading/conversion bug, the other is an OOM problem; not the same underlying defect." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "Weight tying/generation garbage text and dtype propagation on BLIP2 are separate model-loading issues." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior is unrelated to PIL backend torchvision requirements." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Both mention multimodal/video handling, but the packet only shows surface overlap; it does not establish the same concrete code path or a mergeable shared fix." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio processor chat-template sampling-rate default and Whisper batch_decode skipping special tokens are unrelated." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Trailing-slash local model warning is unrelated to Qwen3 MoE weight conversion/loading issues." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Importing GenerationMixin and custom compute_loss signature breakage are separate API regressions." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Tokenizer BOS/EOS handling and Kimi-K2.5 codec handling are different tokenizer regressions." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and Strix Halo mmap/OOM are different memory/loading problems." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading is unrelated to composite Qwen config unwrapping." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer token-count tracking and GPT-oss perplexity are unrelated training issues." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Video-token counting helper bug and batched video processor shape bug are different layers and not clearly the same defect." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "mdeberta special-token insertion and LlamaTokenizer pre-tokenizer override are distinct tokenizer regressions." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE loading/conversion bug and Qwen3-VL weight-shape mismatch are not the same issue." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "CPU-offload device mismatch for bark-small is unrelated to Qwen3_MoeTextRotaryEmbedding CPU-offload compatibility." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Hidden-state output bug and version-dependent tokenization change are not the same code-path problem." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetr output drift in v5 and Qwen3.5 visual-encoder save_pretrained keys are unrelated regressions." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary is mostly grounded, but it overstates the evidence for the 43329 \u2194 44479 link. The packet only shows surface overlap in multimodal/video processing; it does not establish that 43329 is the underlying helper bug behind 44479 or that they share the same code path in a mergeable way. The canonical/best-issue choice may be reasonable, but the wording should stay more conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 18, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:28282", + "issue:29127", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:38175", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43404", + "issue:43452", + "issue:43526", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43782", + "issue:43824", + "issue:43906", + "issue:43927", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44560", + "issue:44737", + "issue:44821", + "issue:44898", + "issue:44912", + "issue:44938", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45137", + "issue:45325", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45538", + "issue:45588", + "issue:45823", + "issue:45907", + "issue:45987" + ], + "soft_pairs": [ + "issue:44291|issue:45042", + "issue:44987|issue:45538", + "issue:42915|issue:43742", + "issue:42915|issue:44821", + "issue:33357|issue:34567", + "issue:43257|issue:43756", + "issue:41720|issue:43540", + "issue:44479|issue:45381", + "issue:43452|issue:43582", + "issue:44987|issue:45907", + "issue:42915|issue:45538", + "issue:43927|issue:44912", + "issue:42175|issue:43824", + "issue:43317|issue:45538", + "issue:43540|issue:44479", + "issue:43540|issue:44560", + "issue:44062|issue:44991", + "issue:42175|issue:44938", + "issue:43577|issue:45072", + "issue:38175|issue:44898", + "issue:42175|issue:44488", + "issue:43404|issue:45987", + "issue:45137|issue:45405", + "issue:28282|issue:34689", + "issue:43906|issue:45381", + "issue:43742|issue:44291", + "issue:42915|issue:43749", + "issue:44737|issue:45588", + "issue:43540|issue:45823", + "issue:43526|issue:45479", + "issue:28282|issue:29127", + "issue:43756|issue:45325", + "issue:43582|issue:43782" + ], + "prepared_review_unit_hash": "a512f17564f5fca5d9a45e40f3ce7bebd70732129b4a4644a10a93184517d1ed", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37711, + "estimated_input_tokens": 9428, + "estimated_eval_tokens": 19112 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft duplicate edges should be accepted from this packet. The only near-match, issue:44479 vs issue:45381, is topical within the same Qwen-VL video-position family but not supported strongly enough to merge as the same underlying bug. The rest are clearly different failures or different code paths.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 44479 is the best issue anchor because it is the broadest and most central report in the Qwen-VL video-position regression family, covering multiple related variants rather than a single narrow symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44479 is the strongest overall issue candidate: it describes the shared video-input regression most directly and spans several Qwen/VL variants, but it should not be treated as a duplicate of 45381 on this evidence.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Different bug classes and code paths: init_empty_weights/_is_hf_initialized vs PIL backend torchvision dependency." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated problems: model loading for one repo vs tokenizer model_max_length behavior." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Different models and failures: Qwen3 MoE FP8 config vs MobileLLM key error." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Only broad model-loading similarity; no concrete shared failure path." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "MacOS CLIP bus error and TrainerState token-count bookkeeping are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Both are model-related, but one is weight conversion with accelerate/deepspeed and the other is RoPE layer count." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Same broad Qwen family, but different concrete failures and paths." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": false, + "reason": "Related Qwen-VL video-position reports, but the evidence is only topical and not strong enough for duplicate acceptance." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Tokenizer/model GGUF loading issue is unrelated to Apple Silicon allocator warmup TypeError." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Different subsystems: revision forwarding in repo file listing vs a model-loading regression." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "No shared concrete bug; Qwen3MoE FP8 loading and tokenizer max-length are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "Config persistence/generation IDs vs quantization fallback are different bug classes." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Packaging/backend inclusion bug and missing class import are not the same issue." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "device_map offload loading failure is unrelated to tokenizer max-length handling." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Both mention video, but the models and failure modes differ." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Different models and errors: Qwen3OmniMoe input validation vs Qwen3-VL-embedding StopIteration." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Tokenizer AddedToken argument conflict is not the same as loading a specific model repo." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Backend installation issue and Python 3.14 load failure are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both are dtype-related, but they affect different model families and likely different paths." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "SigLIP2 zero probabilities and Perceiver interpolation failures are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Backend packaging issue vs model load failure; not duplicates." + }, + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "Tied-weight bug in Mistral3 is unrelated to StaticCache returning the wrong type." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error has nothing to do with the PEFT version bump." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "General PyTorch import error vs a specific vision model-loading regression; different causes." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "One is an isolated reproduction reference, but not the same concrete bug as the Qwen2.5-VL video-position regression." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "Both are loading issues, but the actual failures differ substantially." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Different distributed-loading problems with different triggering conditions." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "XLNet CPU placement bug is unrelated to flash-attention sink-less model crash." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Different models and code paths: Qwen3OmniMoe video input error vs Gemma4 PLE device mismatch." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Beit label reduction bug is unrelated to sequence-classification zero-loss behavior." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "PyTorch missing import error and LayoutLMv3 box-content validation message are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both touch RoPE/position logic, but the concrete bugs are different." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "Allocator TypeError on Apple Silicon and Qwen3VL weight_only loading error are distinct failures." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The writeup overstates the evidence in the packet. In particular, the claimed accepted duplicate edge between issue:44479 and issue:45381 is not supported here: the packet marks that soft pair as deterministic_accept=false, and the similarity is only topical, not enough to justify acceptance. Because the summary leans on that unsupported acceptance, it is not conservative enough." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 19, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:24643", + "issue:29127", + "issue:34567", + "issue:36331", + "issue:41762", + "issue:43295", + "issue:43452", + "issue:43493", + "issue:43531", + "issue:43577", + "issue:43643", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43819", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44466", + "issue:44484", + "issue:44488", + "issue:44514", + "issue:44589", + "issue:44625", + "issue:44704", + "issue:44792", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44964", + "issue:45005", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45290", + "issue:45356", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45600", + "issue:45823", + "issue:45920" + ], + "soft_pairs": [ + "issue:43493|issue:43994", + "issue:34567|issue:36331", + "issue:44291|issue:44821", + "issue:44062|issue:45081", + "issue:45357|issue:45920", + "issue:43643|issue:45375", + "issue:43452|issue:44488", + "issue:44792|issue:44964", + "issue:45042|issue:45081", + "issue:43742|issue:44589", + "issue:43531|issue:44821", + "issue:45405|issue:45600", + "issue:43697|issue:45216", + "issue:43688|issue:43749", + "issue:44514|issue:45381", + "issue:44484|issue:44704", + "issue:43720|issue:44898", + "issue:41762|issue:44936", + "issue:24643|issue:29127", + "issue:44625|issue:44877", + "issue:43452|issue:44843", + "issue:44514|issue:45290", + "issue:44466|issue:45005", + "issue:43295|issue:45356", + "issue:43452|issue:43577", + "issue:43819|issue:44811", + "issue:44936|issue:45823" + ], + "prepared_review_unit_hash": "4286c10dfb75180238aeb880b92e16b61ff6b3273d83460cfbeed60394065476", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36185, + "estimated_input_tokens": 9047, + "estimated_eval_tokens": 18350 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a mix of unrelated Transformers bug reports; only a couple of pairs look like true duplicates or near-duplicates. The strongest shared themes are SigLIP2 output regressions and tied-weights serialization issues.", + "confidence": 0.83, + "canonical_issue_reason": "Issue 45920 is the broadest and most actionable representative: it is an open, current v5 regression affecting AutoTokenizer across multiple models, which makes it the best cluster anchor among otherwise heterogeneous reports.", + "canonical_pr_reason": null, + "best_issue_reason": "45920 is the best overall issue to keep: it is open, directly user-facing, and spans multiple affected models rather than a single niche symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Both report SigLIP2 producing incorrect outputs; one frames it as a HF-vs-JAX discrepancy and the other as nonsensical results via AutoModel/pipeline, which looks like the same underlying model bug." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Both are training-related regressions, but one is about TrainerState token counting and the other is a compute_loss signature change; different failures and code paths." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "These involve unrelated loading failures: init_empty_weights/_is_hf_initialized versus loading AutoImageProcessor from URL." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer issues, but one is AddedToken construction and the other is a Mistral regex/backend_tokenizer crash; not the same bug." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Different subsystems: Qwen3.5 save_pretrained visual key serialization versus global AutoTokenizer token-id regression." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both concern config handling, but the root causes differ: missing fields from trust_remote_code AutoConfig versus a specific Qwen3_5MoeVisionConfig field being dropped by strict parsing." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading complaints, but gguf_file breakage and a specific cjvt/sleng-bert load failure do not point to the same code-path." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Both are multimodal model failures, but they affect different models and symptoms; not enough to treat as one bug." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "PIL/torchvision backend requirements are unrelated to the Mistral tokenizer AttributeError." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "Different loading errors: a key error for MobileLLM versus missing Float8 storage object." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to AutoImageProcessor URL loading." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "These are unrelated CI/dependency/config-reference issues." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Different regressions: RTDetrV2 output mismatch versus Qwen3.5 checkpoint saving correctness." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are distinct problems." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL issues, but one is chat-template batching and the other is video vision_position_ids; different code paths." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "A save_pretrained sharding-size question is unrelated to AutoProcessor kwargs forwarding." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight loading and Perceiver image classification failures are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed ZeRO-3 Gemma3 loading and trainer.evaluate-after-train failures are separate issues." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "One is a DeepSpeed training RuntimeError; the other is a LayoutLMv3 error-message clarity issue." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "num_labels propagation in Qwen3.5 and strict config blocking granite_speech are different configuration bugs." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "gguf_file loading breakage and offline mistral-regex model_info calls are unrelated tokenizer/loading bugs." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both are apply_chat_template crashes, but the triggers differ substantially: batched padding=False versus assistant tool-call messages with no content." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": true, + "reason": "Both point to tied-weights serialization problems in v5; the device-dependent lm_head.weight behavior and translation-model tied-weight breakage are plausibly the same save_pretrained bug." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Processor/tokenizer access regressions and Kimi-K2.5 codec/fix_mistral_regex issues are different tokenizer bugs." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC from_latents/STE mismatch and Whisper batch_decode skip_special_tokens handling are unrelated." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "Trainer evaluate failure and Gemma4 device mismatch during forward are separate runtime issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The canonical issue choice is supported by the packet: 45920 is open, user-facing, and spans multiple models under a single AutoTokenizer v5 regression. The two accepted soft pairs are plausible duplicates/near-duplicates based on titles alone, and the rejected pairs are mostly appropriately cautious. I don\u2019t see material overstatement." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 20, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:28282", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:38175", + "issue:41720", + "issue:43122", + "issue:43278", + "issue:43295", + "issue:43452", + "issue:43504", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44451", + "issue:44464", + "issue:44479", + "issue:44554", + "issue:44561", + "issue:44568", + "issue:44610", + "issue:44625", + "issue:44743", + "issue:44821", + "issue:44843", + "issue:44977", + "issue:44991", + "issue:45440", + "issue:45491", + "issue:45588", + "issue:45701", + "issue:45704", + "issue:46002" + ], + "soft_pairs": [ + "issue:38175|issue:43295", + "issue:30064|issue:33666", + "issue:44464|issue:44743", + "issue:43653|issue:44361", + "issue:44361|issue:44442", + "issue:43643|issue:44561", + "issue:43653|issue:44568", + "issue:41720|issue:43906", + "issue:43688|issue:45440", + "issue:43688|issue:45704", + "issue:28282|issue:32090", + "issue:28282|issue:33357", + "issue:45491|issue:46002", + "issue:43577|issue:43697", + "issue:28282|issue:35141", + "issue:44843|issue:44991", + "issue:43688|issue:45701", + "issue:43646|issue:43749", + "issue:43653|issue:43927", + "issue:43531|issue:43742", + "issue:43550|issue:43927", + "issue:44464|issue:44977", + "issue:44479|issue:44625", + "issue:43550|issue:44361", + "issue:43577|issue:44554", + "issue:43122|issue:43906", + "issue:43577|issue:45588", + "issue:43504|issue:43550", + "issue:32090|issue:34567", + "issue:41720|issue:44464", + "issue:43504|issue:43720", + "issue:43504|issue:44610", + "issue:32090|issue:33666", + "issue:43452|issue:44451", + "issue:43742|issue:44821", + "issue:43278|issue:43688" + ], + "prepared_review_unit_hash": "de34865d7e6df05cc33f45c023f0045a527f78b8661131f50d118943e5d080b1", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38481, + "estimated_input_tokens": 9621, + "estimated_eval_tokens": 19498 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is largely heterogeneous. A few items share a broad tokenizer/regression theme, but none of the soft pairs appear to be the same underlying bug or change, so all soft edges are rejected.", + "confidence": 0.86, + "canonical_issue_reason": "Issue #45701 is the broadest, most umbrella-like report in the set: it explicitly centers on version-dependent tokenization changes, which is the only recurring theme spanning multiple nearby issues.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45701 is the best representative issue for this cluster because it is the most general tokenization-regression report and has inbound attention, even though the cluster is too mixed to collapse into one duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Unrelated failures: SigLIP2 zero probabilities vs custom model init/processor.tokenizer regression." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Different domains and bugs: void segmentation maps vs Qwen2-VL multi-GPU training." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both are Qwen-related, but one is compiled-forward chunked generation inconsistency and the other is recurrent-state reset in modular code; different code paths." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Tokenizer issues, but different models and symptoms: BigBird special-token registration vs MLuke task AttributeError." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Different tokenizer loaders and different exceptions; no clear shared underlying bug." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "One is missing fields from trust_remote_code config loading; the other is a v5.0 API removal breaking trust_remote_code models." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both involve special tokens, but they affect different tokenizers and different behaviors (decode output vs BOS/EOS addition)." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "No concrete overlap: Qwen3 A800 cudaErrorAssert vs an isolated reproduction of a different issue." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "MoE-related but different defects: auxiliary-loss normalization vs divergence from the remote DeepSeekV3 implementation." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Completely different bugs: MoE loss normalization vs T5/apex RMSNorm memory leak." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "ImportError for missing PyTorch vs Trainer NoneType broadcast error; unrelated." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "Missing PyTorch ImportError vs MacOS bus error in CLIP loading; unrelated." + }, + { + "left": "issue:45491", + "right": "issue:46002", + "accept": false, + "reason": "Both mention NaNs, but the trigger and code path differ: sliding-window/all-padding embeddings vs classification-head NaNs after checkout/init." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Different model families and failures: BLIP2 dtype propagation vs RTDetrV2 output divergence." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but one is an offline model_info call in _patch_mistral_regex and the other is a specific tokenizer load failure." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Different defect types: auxiliary-loss normalization vs broad tokenization version-change report." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Custom model initialization breakage vs FSDP CPU RAM efficient loading; different subsystems and bugs." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Both are token-related, but one is special-token registration and the other is config loss of custom token IDs; not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding-window issue vs MobileLLM pretrained load KeyError; unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile + SDPA failure vs token-ID persistence/config bug; unrelated." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both affect generation, but one is compiled-forward chunked generation inconsistency and the other is a flash-attention regression in Qwen3.5." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "torch.compile/SDPA bug vs tokenizer AttributeError; unrelated." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype propagation vs an MPS attention correctness issue; different models and failure modes." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Version-dependent tokenization change vs isolated reproduction of a different issue; no shared underlying bug." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Dtype propagation bug vs flash_attention crash on s_aux=None; unrelated." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Pretrained load legacy-field issue vs Bamba torch.compile/SDPA failure; unrelated." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer broadcast TypeError vs TrainerState counter not updating; different training bugs." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Qwen3 auto device mapping assert vs chunked generation inconsistency under compile; different problems." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Legacy-field model loading bug vs BitNet packed-weight unpacking issue; different code paths." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Pretrained-load legacy field vs processor/model input-size mismatch; unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer broadcast NoneType error vs Qwen2-VL multi-GPU training request; unrelated." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "Both are load failures, but one is gguf_file breaking AutoTokenizer/AutoModel loading and the other is a specific tokenizer load regression for ScandiBERT." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Different loading failures: MobileLLM KeyError vs AutoImageProcessor-from-URL problem." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Embedding dtype drift in evaluate vs MoE auxiliary-loss normalization; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 21, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:28218", + "issue:33357", + "issue:33666", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:43257", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43540", + "issue:43572", + "issue:43606", + "issue:43646", + "issue:43720", + "issue:43756", + "issue:43824", + "issue:43825", + "issue:43844", + "issue:43927", + "issue:44291", + "issue:44361", + "issue:44466", + "issue:44488", + "issue:44568", + "issue:44589", + "issue:44625", + "issue:44843", + "issue:44849", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45357", + "issue:45405", + "issue:45759", + "issue:45803", + "issue:45812", + "issue:45823", + "issue:45987", + "issue:46002" + ], + "soft_pairs": [ + "issue:33666|issue:36010", + "issue:44849|issue:45357", + "issue:43525|issue:43572", + "issue:43606|issue:43927", + "issue:43493|issue:43825", + "issue:43262|issue:43295", + "issue:43720|issue:43927", + "issue:43756|issue:44913", + "issue:44568|issue:45812", + "issue:44625|issue:46002", + "issue:28218|issue:33357", + "issue:43720|issue:44361", + "issue:33666|issue:36331", + "issue:39692|issue:43493", + "issue:43540|issue:44977", + "issue:44964|issue:45405", + "issue:43334|issue:43572", + "issue:43493|issue:43844", + "issue:45803|issue:45987", + "issue:43278|issue:43844", + "issue:43756|issue:45083", + "issue:43334|issue:45759", + "issue:43257|issue:43299", + "issue:45200|issue:45229", + "issue:44488|issue:44843", + "issue:39692|issue:43295", + "issue:43824|issue:44589", + "issue:43646|issue:44466", + "issue:45229|issue:45823", + "issue:43504|issue:43606", + "issue:43572|issue:44291", + "issue:33357|issue:33666" + ], + "prepared_review_unit_hash": "bc8f37e8a49d788e686189c8b68229a942673e29a887c121d5dff9303f3275bb", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37566, + "estimated_input_tokens": 9392, + "estimated_eval_tokens": 19040 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of mostly unrelated Transformers issues: tokenizer regressions, config/save-load bugs, multimodal model loading problems, training/runtime errors, and a few docs/CI reports. The soft-similarity edges are mostly superficial subsystem overlap rather than the same underlying defect.", + "confidence": 0.68, + "canonical_issue_reason": "issue:45812 is the strongest representative issue in the set: it describes a concrete, cross-model v5 tokenizer regression with multiple inbound references, and it is broader and clearer than the more model-specific reports around it.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 is the best issue to anchor the cluster because it is a clearly articulated, high-signal regression report affecting a broad class of models, whereas most other issues are narrower or unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Multi-GPU training support request vs an import error during model loading; different code paths and no shared bug." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Different Qwen3.5 bugs: output_hidden_states behavior vs incorrect visual encoder keys on save; not the same defect." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both mention missing pad token fields, but they affect different model configs and likely different serialization bugs." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch for bark-small vs DiaConfig token ID loss after save/load; unrelated failures." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation mismatch vs pipeline translation error messaging; no common underlying code change." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Both involve multimodal processors, but one is an audio sampling-rate default and the other is a processor/tokenizer regression." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "Packed-weight loading bug in BitNet vs DiaConfig token-ID persistence bug; different models and mechanisms." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "RoPE-layer drop in Smollm3 vs GPTNeoX rotary_pct reload issue; same broad area, but not the same bug." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different tokenizers/models and different wrong behaviors." + }, + { + "left": "issue:44625", + "right": "issue:46002", + "accept": false, + "reason": "Config propagation bug for Qwen3.5 vs NaNs in classification heads at init; unrelated symptoms." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer spacing bug vs MacOS bus error loading a CLIP model; no shared underlying issue." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "BitNet packed-weight loading failure vs MLukeTokenizer task AttributeError; different components and failures." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Multi-GPU training request vs custom trainer signature incompatibility; not the same defect." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Documentation example errors vs a model implementation discrepancy; related model family, but different bug class." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Video-input processing error in Qwen3OmniMoe vs flash-attention generation bug in Qwen3.5; different code paths." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Model load failure vs a dependency version bump; unrelated issues." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Missing pad_token_id on Qwen3-VL vs missing pad_token_idx on StableLm; similar wording, but different configs/models and likely different fixes." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 JAX/HF mismatch vs DeepSpeed gradient inflation; completely different problems." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare except in Fuyu tensor conversion vs StaticCache returning the wrong type; unrelated bugs." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Dtype drift between train/eval vs ZeRO-3 gradient increase; not the same bug." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "Smollm3 RoPE-layer issue vs qwen3_omni_moe feature-length helper behavior; different model families and code paths." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Qwen3-VL missing pad_token_id vs AutoModelForCausalLM not unwrapping text_config for composite configs; related family only, not same issue." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Accelerate+deepspeed conversion bug for Qwen3 MOE weights vs transformers dev loading breakage for Qwen3VL MOE; distinct regressions." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Text-only fine-tuning token-type default vs multi-GPU inference OOM; unrelated issues." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "Model load failure for a specific repo vs offline-mode breakage in AutoTokenizer patching; different root causes." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "Docs example problems vs processor/tokenizer regression in custom model code; not the same bug." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "ImportError for a Qwen VL class vs missing Float8 storage type; unrelated runtime failures." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "General custom model initialization breakage vs inconsistent lm_head serialization by device; different concrete behaviors." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "CUDA OOM in Gemma4 multi-GPU inference vs device mismatch during forward with device_map='auto'; different failure modes." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field model-loading issue for BEiT vs CPU offload device mismatch for bark-small; unrelated." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Missing pad_token_idx in a config vs init_empty_weights rejecting _is_hf_initialized; different APIs and bugs." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "MacOS bus error on a CLIP model vs Qwen2-VL multi-GPU training request; no common underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 22, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29942", + "issue:30333", + "issue:34567", + "issue:37428", + "issue:38175", + "issue:42490", + "issue:43232", + "issue:43278", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43575", + "issue:43582", + "issue:43606", + "issue:43653", + "issue:43696", + "issue:43701", + "issue:43844", + "issue:43927", + "issue:43957", + "issue:43994", + "issue:44112", + "issue:44315", + "issue:44361", + "issue:44423", + "issue:44464", + "issue:44493", + "issue:44521", + "issue:44554", + "issue:44589", + "issue:44734", + "issue:44792", + "issue:44849", + "issue:44964", + "issue:44977", + "issue:45072", + "issue:45084", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45405", + "issue:45446", + "issue:45520", + "issue:45584", + "issue:45823" + ], + "soft_pairs": [ + "issue:44589|issue:45520", + "issue:43927|issue:44361", + "issue:44423|issue:44734", + "issue:43504|issue:43653", + "issue:44464|issue:45584", + "issue:43606|issue:44112", + "issue:43994|issue:44493", + "issue:43575|issue:45405", + "issue:43278|issue:43701", + "issue:44792|issue:45405", + "issue:29942|issue:30333", + "issue:42490|issue:43696", + "issue:44521|issue:45290", + "issue:43844|issue:44964", + "issue:28218|issue:34567", + "issue:44554|issue:45446", + "issue:45084|issue:45520", + "issue:43582|issue:44977", + "issue:43540|issue:45200", + "issue:15354|issue:38175", + "issue:43232|issue:44849", + "issue:37428|issue:43957", + "issue:45072|issue:45198", + "issue:45200|issue:45823", + "issue:44315|issue:44849", + "issue:43493|issue:43701" + ], + "prepared_review_unit_hash": "fd6be3534eeb26b48acf08a7a4c17a3e56164cf8e5002c49071a5bb07744888d", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 34877, + "estimated_input_tokens": 8720, + "estimated_eval_tokens": 17696 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: most items are unrelated bug reports that only share broad subsystem words (tokenization, generation, flash-attn, device/dtype, serving). None of the soft pairs look like the same underlying bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Both are import/runtime failures, but they affect different symbols and failure modes; not the same bug." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "One is config save/load causing generation index errors; the other is a tokenizer AttributeError in tasks." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both involve serve, but one crashes on multimodal input conversion and the other on KV-cache continuation indexing." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Different components and symptoms: BEiT legacy-field loading vs BigBirdTokenizer special-token registration." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Both are generation-related, but one is compiled forward inconsistency and the other is empty-transcription/chat-template behavior." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Different models and code paths; one is CPU offload device mismatch, the other is a stale CI test override." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "Different bugs: SigLIP2 wrong outputs vs a broad position-id key warning across many models." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "OOM during tensor-parallel model load is unrelated to a PEFT version requirement issue." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "Embedding dtype drift and checkpoint key mismatch are unrelated training/eval issues." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "A janus image-generation test failure is unrelated to the PEFT version bump." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "FlashAttention test failures and MLFlow reporting on failed jobs are different subsystems and failures." + }, + { + "left": "issue:42490", + "right": "issue:43696", + "accept": false, + "reason": "Import warning on trailing-slash paths is unrelated to a GPT-oss OOM." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both are apply_chat_template issues, but one is multimodal assistant masks and the other is tool-call content handling." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient growth and Phi-4 multimodal loading are unrelated problems." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing after added tokens is unrelated to TrainerState token-count tracking." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "Different flex-attention/MPS correctness and version-check issues; no shared code-path bug." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Compile-time node handling and flash-attn import lookup are unrelated." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator TypeError and Qwen3.5 flash-attention output issues are different failures." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-input processing in Qwen3OmniMoe is not the same as Gemma 4 token-type defaults for text-only fine-tuning." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export failure and SigLIP2 zero-probability outputs are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is a different bug from Qwen3.5 hidden-states behavior." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Missing flash-attention helper import and meta-device model-loading breakage are distinct issues." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "Bfloat16 dtype mismatches and Wav2Vec2 save/tokenization failures do not share the same underlying bug." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Token-type-id defaults and Gemma4 PLE device mismatch are different problems." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel not applied with model_init is unrelated to Qwen3.5 output_hidden_states behavior." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 JAX/HF discrepancy and resume-from-checkpoint key mismatch 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": 1, + "component_count": 17, + "review_unit_index": 23, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:28218", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:42490", + "issue:42915", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43388", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43575", + "issue:43653", + "issue:43819", + "issue:43824", + "issue:43827", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43901", + "issue:43957", + "issue:43975", + "issue:44112", + "issue:44206", + "issue:44442", + "issue:44466", + "issue:44514", + "issue:44521", + "issue:44554", + "issue:44610", + "issue:44792", + "issue:44898", + "issue:44936", + "issue:44987", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45245", + "issue:45325", + "issue:45356", + "issue:45412", + "issue:45563", + "issue:45584" + ], + "soft_pairs": [ + "issue:43295|issue:44610", + "issue:44554|issue:45356", + "issue:44898|issue:45412", + "issue:44466|issue:45127", + "issue:43572|issue:44987", + "issue:44792|issue:45563", + "issue:37428|issue:43824", + "issue:43572|issue:43957", + "issue:45200|issue:45325", + "issue:43295|issue:43450", + "issue:43844|issue:44936", + "issue:43334|issue:43525", + "issue:43824|issue:43975", + "issue:43295|issue:43873", + "issue:43388|issue:43526", + "issue:42915|issue:43824", + "issue:38175|issue:45412", + "issue:38175|issue:43493", + "issue:44514|issue:44521", + "issue:44442|issue:45198", + "issue:28218|issue:35141", + "issue:42490|issue:43493", + "issue:43278|issue:43856", + "issue:43653|issue:44112", + "issue:43450|issue:43575", + "issue:43827|issue:43901", + "issue:44206|issue:45584", + "issue:45127|issue:45245", + "issue:43819|issue:45083" + ], + "prepared_review_unit_hash": "9cb2039c1dd20c5ddd9fb136ad8c12400b4491ed915f9e424b458496ef22e61d", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36673, + "estimated_input_tokens": 9169, + "estimated_eval_tokens": 18594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These soft edges are mostly false positives: they share broad subsystem or model-family overlap, but not the same concrete bug. No PRs are present. The set is heterogeneous overall, with no strong duplicate cluster.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 44521 is the closest thing to a cluster anchor because it is open, recent, and has the highest user-facing activity among the remaining items, but the surrounding issues are too heterogeneous to treat it as a true canonical duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "44521 is the best overall representative only in the loose sense of being the most active, general multimodal regression here; it is not a valid dedup target for the other items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Both are multimodal processor regressions, but one is a processor.tokenizer/image-handling regression and the other is a video/input-size mismatch; different code paths and fixes." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "One is an MPS attention correctness bug; the other is a tokenizer codec/warning regression. No shared underlying defect." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver interpolation failure and RT-DETR memory release are unrelated bugs in different models/subsystems." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Both involve tied/serialization semantics, but one is inconsistent lm_head serialization by device and the other is LoRA merge collapse after vocab extension; not the same fix." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Both are model-loading regressions, but the reported symptoms and likely causes differ; too little evidence they are the same bug." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image-generation test failure and a stale paged-generate warning are distinct generation issues." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are ImportErrors, but for different missing symbols in different modules; not the same underlying import breakage." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "One is a missing pad_token_idx config regression; the other is a meta-device model-loading failure affecting some models. Not the same bug." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma 4 mm_token_type_ids defaulting and Qwen2.5-VL rope-index scaling are separate model-specific correctness issues." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Both touch processors, but one is about processor.tokenizer/image routing and the other is batched video output shape; different defects." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "Gradient explosion under ZeRO-3 and evaluate() failing after train() are not the same training-state problem." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Same symptom class (missing pad_token_id), but different config classes/models and no evidence of a shared root cause." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "An import error for Qwen2.5-VL and a detokenization regression in DeepSeek Coder are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor-tokenizer regression vs quantization offloading behavior; too different to merge." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Both concern labels, but one drops tuple label elements in gather_for_metrics while the other reduces labels incorrectly in an image processor; not the same path." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "FP8-config failure in Qwen3MoE and a Qwen2.5-VL import error are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero-probability behavior and RT-DETR memory cleanup are entirely different bugs." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Both are SigLIP2-related, but one reports zero probabilities and the other a broader HF-vs-JAX discrepancy; not enough to treat as the same concrete bug." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Same processor family and similar API surface, but one is a batched padding=False crash and the other is zero assistant masks for multimodal inputs; different failure modes." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different tokenizer/model families and different failure modes: loading FastSpeech2ConformerTokenizer vs save_pretrained/tokenization failures in Wav2Vec2." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer spacing after added tokens and embedding reinitialization after resize are separate tokenizer/model-weight bugs." + }, + { + "left": "issue:42490", + "right": "issue:43493", + "accept": false, + "reason": "Path-with-trailing-slash import warning and SigLIP2 implementation discrepancy are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Training/eval dtype drift and Qwen3 MoE memory inefficiency are different problems." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and a GraniteSpeech CI device-override test failure do not share the same bug." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Batched video processor shape bug and tensor-parallel OOM while loading a large model are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs regressions about pipelines, but they refer to different pipeline APIs and deprecations; not duplicates." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Unsupported center argument in a feature extractor and Whisper empty-transcription failure after align_special_tokens are different audio bugs." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA/tied-weights collapse after vocab extension is unrelated to the 2^24 category limit runtime error." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent/STE mismatch and qwen3_omni_moe feature-length helper behavior are unrelated 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": 1, + "component_count": 17, + "review_unit_index": 24, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:43262", + "issue:43278", + "issue:43335", + "issue:43425", + "issue:43450", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43825", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44292", + "issue:44351", + "issue:44360", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44561", + "issue:44610", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:45072", + "issue:45083", + "issue:45200", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45478", + "issue:45520", + "issue:45588", + "issue:45593", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:43262|issue:43450", + "issue:43819|issue:44112", + "issue:44610|issue:44857", + "issue:37428|issue:43425", + "issue:43335|issue:43550", + "issue:43606|issue:45083", + "issue:45290|issue:45381", + "issue:44448|issue:44743", + "issue:44857|issue:45593", + "issue:45200|issue:45588", + "issue:43278|issue:43825", + "issue:37428|issue:44351", + "issue:44360|issue:44561", + "issue:29942|issue:32090", + "issue:44206|issue:45823", + "issue:43611|issue:43931", + "issue:39692|issue:43526", + "issue:43335|issue:43653", + "issue:43819|issue:44493", + "issue:43550|issue:44112", + "issue:43335|issue:43504", + "issue:44855|issue:45083", + "issue:45310|issue:45478", + "issue:43335|issue:45083", + "issue:29127|issue:32090", + "issue:45588|issue:45859", + "issue:39692|issue:44493", + "issue:44292|issue:45520", + "issue:44448|issue:44779", + "issue:38175|issue:44493", + "issue:43335|issue:45072", + "issue:43335|issue:44112", + "issue:44462|issue:44561", + "issue:44561|issue:44779", + "issue:43720|issue:44112" + ], + "prepared_review_unit_hash": "6fd9d30c8f8c0aeffc2e20a26b81b7d0f1cead8db6e9f43239e1f0011357da02", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37677, + "estimated_input_tokens": 9420, + "estimated_eval_tokens": 19096 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly unrelated issue reports; there is one clear duplicate pair: the Qwen3.5 MoE `from_pretrained` regression in issue:45310 and issue:45478. The rest share broad subsystem keywords but describe different bugs/code paths.", + "confidence": 0.95, + "canonical_issue_reason": "issue:45310 is the earlier, fuller report of the same Qwen3.5 MoE `from_pretrained` regression; issue:45478 is a near-identical follow-up.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best canonical anchor because it captures the duplicated bug clearly and predates the later duplicate report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Different processors and failures: audio chat template sampling-rate default vs batched video shape bug." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "Different models and code paths: DAC latent/STE mismatch vs GraniteSpeech CI device override test." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Different components and symptoms: processor input size mismatch vs LwDetr loss AMP crash." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "One is an import error for a flash-attn helper; the other is broad Torch 2.10 compatibility." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "Different model families and bugs: SwitchTransformers config layer creation vs Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch for Bark vs a helper length-calculation bug in qwen3_omni_moe." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Different failures: chat template with tool calls vs Qwen2.5-VL video position IDs." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output regression is unrelated to Qwen recurrent-state reset logic." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "Different training-time failures: float16 AMP crash in LwDetrImageLoss vs missing auxiliary losses in D-FINE." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 `mm_token_type_ids` defaulting issue is unrelated to flash_attention `s_aux=None` crash." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype drift during evaluate is not the same as the v5 pipeline translation-task error message bug." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and causes (`_flash_supports_window_size` vs `HybridCache`)." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer ReLU discussion is unrelated to removal of `is_torch_fx_available` breaking trust_remote_code models." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and Trainer `_gpu_broadcast_one` NoneType errors are different issues." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Unsupported `center` arg in LasrFeatureExtractor is unrelated to Gemma4 PLE device mismatch under `device_map=\"auto\"`." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Generic `base_model_prefix` loading breakage is not the same as Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 docs/model mismatch and quantization failure is unrelated to BeitImageProcessorFast `reduce_labels` truncation." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to BigBirdTokenizer mask-token decode behavior." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC forward/latent mismatch is unrelated to the position-id key issue affecting many models." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba torch.compile SDPA failure is unrelated to the GraniteSpeech CI stale device override test." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers layer-count config bug is unrelated to Beit pretrained preset loading with legacy fields." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 `IndentationError` in DebertaV2 import is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same Qwen3.5 MoE `from_pretrained` regression, with matching title and failure mode." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation is unrelated to the bfloat16 dtype mismatch in inference." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 box-clarity error message and Trainer `_gpu_broadcast_one` TypeError are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Both involve Qwen3_5/MoE/offload, but one is a flash_attention `s_aux=None` crash and the other is a rotary-embedding CPU-offload incompatibility." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 docs/quantization issue is unrelated to the position-id key regression." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime failure is not the same as the Python 3.13 `flash_attn` import KeyError." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output differences and DeepSeek tokenizer regressions are different bugs." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 zero-probabilities bug is unrelated to the position-id key regression." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "Same as the other SwitchTransformers/dtype pair: unrelated bugs in the same broad area." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "SwitchTransformers config bug and GraniteSpeech CI device override test are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer.json loading behavior and `is_torch_fx_available` removal are unrelated regressions." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Trust-remote-code breakage from helper removal is unrelated to DeepSeek tokenizer output changes." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet accelerate unpacking bug is unrelated to the GraniteSpeech stale device override test." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The one accepted duplicate pair (issue:45310 / issue:45478) is well-supported by matching titles and the same Qwen3.5 MoE from_pretrained regression, and the rest of the soft-edge rejections are phrased cautiously without overstating evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 25, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:10000", + "issue:15354", + "issue:28218", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:34689", + "issue:35141", + "issue:37428", + "issue:40444", + "issue:41720", + "issue:42490", + "issue:43278", + "issue:43329", + "issue:43412", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43701", + "issue:43723", + "issue:43854", + "issue:43873", + "issue:43927", + "issue:43976", + "issue:44448", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44857", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45563", + "issue:45588", + "issue:45698", + "issue:45712", + "issue:45803" + ], + "soft_pairs": [ + "issue:44977|issue:45229", + "issue:42490|issue:43854", + "issue:40444|issue:43526", + "issue:34689|issue:35141", + "issue:44448|issue:44977", + "issue:43606|issue:44857", + "issue:43723|issue:44554", + "issue:44857|issue:45072", + "issue:28218|issue:32090", + "issue:44977|issue:45563", + "issue:43927|issue:45698", + "issue:43701|issue:45083", + "issue:44568|issue:45491", + "issue:43550|issue:45083", + "issue:37428|issue:44987", + "issue:45198|issue:45803", + "issue:29942|issue:35141", + "issue:45372|issue:45588", + "issue:43873|issue:44493", + "issue:32090|issue:33357", + "issue:45459|issue:45712", + "issue:43873|issue:45229", + "issue:45245|issue:45563", + "issue:43412|issue:45588", + "issue:43278|issue:43329", + "issue:41720|issue:45229", + "issue:10000|issue:15354", + "issue:43976|issue:45440", + "issue:42490|issue:43575", + "issue:45372|issue:45406" + ], + "prepared_review_unit_hash": "6c1dda20d1cfded88b308eefeb07a2750a3a65dde9cac36b07ff6983183be230", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36341, + "estimated_input_tokens": 9086, + "estimated_eval_tokens": 18428 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is very heterogeneous: most items are unrelated issues spanning tokenization, model loading, precision/device-mismatch, attention kernels, and multimodal processor bugs. None of the soft-edge pairs look like true duplicates of the same underlying bug/change.", + "confidence": 0.95, + "canonical_issue_reason": "Issue #42490 is the clearest generic loading-path bug in the set, with a reproducible and narrowly scoped root cause (local model path normalization trailing slash).", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #42490 is a good representative because it is a concrete, user-facing loading regression with a clear failure mode and likely straightforward fixability.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Different failure modes and subsystems: flash-attention generation behavior vs multi-GPU CUDA OOM." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Both are loading-related, but one is a path-trailing-slash warning and the other is a specific model-load failure for a named checkpoint." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Unrelated areas: multimodal iterable dataset finetuning vs BeitImageProcessorFast label reduction." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model loading regression vs token-embedding resize/post-init reinitialization; not the same bug." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Different models and errors; Pegasus output drift across versions is not the same as Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch is a different concrete bug than float16 AMP crashes in LWDETR loss." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are unrelated code paths." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "Both mention dtype/precision, but they affect different models and different execution paths; not one bug." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer spacing after added token is unrelated to Trainer broadcast TypeError." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation failure vs a stale warning in paged generate(); different underlying issues." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load flows, but one loses custom token IDs in config and the other loads the wrong custom module; distinct defects." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint key mismatch is unrelated to the qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token handling and Gemma3 NaN embeddings are different bugs." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA failure for Bamba is unrelated to qwen3_omni_moe feature-length computation." + }, + { + "left": "issue:37428", + "right": "issue:44987", + "accept": false, + "reason": "Both are load-time issues around flash attention, but the concrete failures and target code paths differ." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure and a bare-except swallowing errors in Fuyu are not the same defect." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization after resize." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 processor loading fails due to a missing dependency import, while the other is a flash-attention AttributeError on sink-less models." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior and unexpected position-id keys are distinct problems." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast NoneType error is unrelated to a MacOS bus error with a CLIP model." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer protobuf error handling and leftover dummy classes are unrelated repository hygiene/runtime issues." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantization offloading behavior is not the same as a multi-GPU OOM during Gemma4 inference." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-cardinality limit error and stale generate warning are unrelated." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export failures and flash-attention sinkless-model AttributeError are different code paths." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype drift in evaluation is unrelated to the undefined video-branch helper issue." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Auto device mapping cudaErrorAssert and CUDA OOM are different failure classes." + }, + { + "left": "issue:10000", + "right": "issue:15354", + "accept": false, + "reason": "German DistilBert issue and torch.jit generator-expression export issue are unrelated and very old." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility issue is unrelated to DeepSeekV3MoE divergence from remote implementation." + }, + { + "left": "issue:42490", + "right": "issue:43575", + "accept": false, + "reason": "Local-path loading warning is unrelated to tensor-parallel OOM on a large Qwen model." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Gemma4 processor import failure and Gemma4Processor missing _tokenizer in serve are different concrete failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 26, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:25251", + "issue:28218", + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:39692", + "issue:42490", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43257", + "issue:43278", + "issue:43381", + "issue:43421", + "issue:43653", + "issue:43756", + "issue:43873", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44610", + "issue:44743", + "issue:44857", + "issue:44871", + "issue:44977", + "issue:45198", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45520", + "issue:45588", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:43065|issue:43994", + "issue:28218|issue:29127", + "issue:43065|issue:45412", + "issue:45372|issue:45459", + "issue:44857|issue:45588", + "issue:44448|issue:44466", + "issue:43653|issue:44743", + "issue:45588|issue:45823", + "issue:43278|issue:43381", + "issue:25251|issue:32090", + "issue:44206|issue:44479", + "issue:43994|issue:45412", + "issue:44186|issue:45198", + "issue:43066|issue:44462", + "issue:44361|issue:45198", + "issue:44451|issue:45520", + "issue:42915|issue:42994", + "issue:44871|issue:44977", + "issue:44265|issue:45198", + "issue:43756|issue:45440", + "issue:29942|issue:30064", + "issue:43421|issue:45491", + "issue:33357|issue:39692", + "issue:43257|issue:43278", + "issue:29127|issue:34567", + "issue:32090|issue:33290", + "issue:42490|issue:43873", + "issue:44610|issue:45412", + "issue:45440|issue:45593" + ], + "prepared_review_unit_hash": "8f232ed4bae1f726392dbc8e96089e6056012ec297a05f53016c5f5789bc8f1b", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35789, + "estimated_input_tokens": 8948, + "estimated_eval_tokens": 18152 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are a broad mix of unrelated tokenizer, loading, training, quantization, and vision bugs. The soft pairs mostly share only broad subsystem overlap, so none look like true duplicates or mergeable PR-equivalents.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Different models and failure modes: Sam3PixelDecoder dummy Conv2d vs SigLIP2 bad AutoModel/pipeline output." + }, + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Tokenizer spacing bug vs LayoutLMv3 error-message clarity issue; unrelated root causes." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Sam3PixelDecoder placeholder layer is unrelated to RT-DETR memory not being released." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma 4 processor import failure and protobuf error masking are separate tokenizer-loading problems." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "LwDetr float16 AMP crash is unrelated to flash-attention s_aux=None handling." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Both are v5 regressions, but one is generation-output drift and the other is tied-weight serialization inconsistency." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token decode bug is unrelated to Qwen recurrent-state reset logic." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Both involve Gemma-related code, but one is a flash-attention AttributeError and the other is a device-map forward mismatch." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Eval-mode dtype change and gradient-checkpointing-in-eval are distinct issues." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nesting regression is unrelated to Trainer NoneType broadcast failure." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported feature arg in LasrFeatureExtractor does not match the Qwen video-input regression." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 inference regression is unrelated to RT-DETR memory cleanup." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 tokenizer NER/padding crash and Wav2Vec2 save/tokenization failure are different code paths." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Wrong tokenizer decoder type and ignoring tokenizer.json are separate tokenizer-loading behaviors." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLuke tokenizer AttributeError is unrelated to Wav2Vec2 save_pretrained/tokenization failure." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model load failure for ScandiBERT and flash_attn KeyError on Python 3.13 are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and quantized-model saving failure are both quantization-related but different bugs." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "EOS config mismatch and flash-attention generation regression are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failure with torch_compilable_check is unrelated to Wav2Vec2 save/tokenization problems." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Different model implementations and defects: RoPE-layer drop vs DeepseekV3MoE divergence." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to void segmentation map processing." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime post-processor update bug and Gemma3 NaN embeddings are unrelated." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error on CLIP model load is unrelated to SigLIP2 documentation-example mistakes." + }, + { + "left": "issue:43257", + "right": "issue:43278", + "accept": false, + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed is unrelated to BF16-to-FP32 eval dtype drift." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and TrainerState token counter updates are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer broadcast TypeError and Adafactor+deepspeed OOM are distinct training issues." + }, + { + "left": "issue:42490", + "right": "issue:43873", + "accept": false, + "reason": "Trailing-slash local model import warning is unrelated to quantization offloading behavior." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch is unrelated to RT-DETR memory retention." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepseekV3MoE implementation divergence and D-FINE auxiliary-loss omission are different model bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 27, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:33357", + "issue:35141", + "issue:36010", + "issue:42490", + "issue:42915", + "issue:43232", + "issue:43262", + "issue:43334", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43646", + "issue:43653", + "issue:43701", + "issue:43761", + "issue:43824", + "issue:43931", + "issue:44062", + "issue:44077", + "issue:44079", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44625", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44977", + "issue:45003", + "issue:45072", + "issue:45103", + "issue:45245", + "issue:45372", + "issue:45440", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45834", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:43824|issue:44279", + "issue:43653|issue:44442", + "issue:43761|issue:45859", + "issue:43526|issue:45834", + "issue:43381|issue:43701", + "issue:45103|issue:45372", + "issue:29942|issue:36010", + "issue:43526|issue:44186", + "issue:29127|issue:33357", + "issue:43334|issue:43531", + "issue:44625|issue:45584", + "issue:44977|issue:45245", + "issue:29127|issue:35141", + "issue:44464|issue:45491", + "issue:42915|issue:43931", + "issue:44442|issue:45072", + "issue:43262|issue:44206", + "issue:43526|issue:44857", + "issue:42490|issue:43381", + "issue:44062|issue:45907", + "issue:43575|issue:43701", + "issue:44743|issue:44811", + "issue:43441|issue:45588", + "issue:43232|issue:43388", + "issue:43646|issue:44077", + "issue:43761|issue:44079", + "issue:43575|issue:44387", + "issue:45003|issue:45440" + ], + "prepared_review_unit_hash": "cd69876bda4584e3eae62d9a3a1df6bfda0eb8b70d8926057462ec7ad151d05b", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36134, + "estimated_input_tokens": 9034, + "estimated_eval_tokens": 18324 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a heterogeneous mix of unrelated Transformers issues (imports, generation, tokenizer/image processor bugs, flash-attention, model-specific regressions). I don\u2019t see a single underlying bug or change that ties them together strongly enough to pick one canonical representative or merge any soft-edge pair.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "One is a specific missing export for `Qwen2_5_VLForConditionalGeneration`; the other is a vague dependency/loading problem with no shared code-path evidence." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer-related, but they affect different models and different failure modes (`BigBirdTokenizer` special-token registration vs `AutoTokenizer` loading `FastSpeech2ConformerTokenizer`)." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "Different model families and bugs: CLIPVision hidden-states regression vs Qwen3_5 MoE rotary embedding CPU-offload incompatibility." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BEiT image processor label reduction bug is unrelated to Kosmos2.5 OCR long-input index errors." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode and checkpoint resume key mismatch are distinct training/runtime issues." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "Auto-docstring annotation handling is unrelated to the `ReasoningEffort` import failure in Gemma 4 processor loading." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failures are not the same as a `GenerationMixin` import removal/visibility issue." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "Different processor/tokenizer code paths and symptoms: label reduction in BEiT vs NER/padding crashes in LayoutLMv2Tokenizer." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error messaging and a MacOS bus error on community CLIP loading are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL `pad_token_id` loading failure and Qwen3-MoE sliding-window behavior are different bugs." + }, + { + "left": "issue:44625", + "right": "issue:45584", + "accept": false, + "reason": "`num_labels` propagation in Qwen3.5 config is unrelated to Whisper empty-transcription generation after token alignment." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation regression is unrelated to the 2^24 category limit runtime error." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error messaging issue and embedding reinitialization in `post_init` are different model behaviors." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Chunked generation with compiled forward and Gemma3 NaN embeddings under mixed-length sliding-window batching are not the same problem." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "FineGrainedFP8Config failure for Qwen3Moe and Qwen3-VL weight-shape mismatch are separate model-loading bugs." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch in unrelated models are different subsystems and code paths." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and LasrFeatureExtractor unsupported-arg crashes are unrelated processor bugs." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "BEiT label reduction and LwDetrImageLoss float16/CUDA crash affect different components and do not share an underlying change." + }, + { + "left": "issue:42490", + "right": "issue:43381", + "accept": false, + "reason": "Local-path slash import warning and gradient-checkpointing-in-eval are unrelated." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "`AddedToken` duplicate `special` argument is unrelated to `list_repo_files` not forwarding `revision`." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Tensor-parallel OOM for Qwen2-57B and resume-from-checkpoint key mismatch are distinct issues." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen3.5 recurrent-state reset bug and Whisper `batch_decode` skip_special_tokens handling are unrelated generation/decoder issues." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Ministral-3 flash-attention failure and sink-less flash_attention.py `s_aux=None` crash are both attention-related but not the same concrete bug." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs update after `sync_gpus` and `gather_for_metrics` dropping tuple labels are unrelated distributed-training bugs." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Custom model initialization breakage in Transformers 5.0.0 and `patchtsmixer` post_init contract change are not the same underlying change." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "CLIPVision hidden_states regression and `ModelOutput` None-key assignment are separate model-output bugs." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both can OOM, but one is TP loading of a specific Qwen model while the other is increased reserved memory under int4 quantization." + }, + { + "left": "issue:45003", + "right": "issue:45440", + "accept": false, + "reason": "Unsafe `sys.modules` access in `modeling_utils` is unrelated to DeepSeekV3MoE divergence from the remote implementation." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 28, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:33290", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:41628", + "issue:42175", + "issue:42490", + "issue:42907", + "issue:43065", + "issue:43316", + "issue:43381", + "issue:43493", + "issue:43525", + "issue:43540", + "issue:43611", + "issue:43643", + "issue:43720", + "issue:43723", + "issue:43749", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44188", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44617", + "issue:44743", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:45137", + "issue:45216", + "issue:45290", + "issue:45372", + "issue:45479", + "issue:45698", + "issue:45759", + "issue:45803" + ], + "soft_pairs": [ + "issue:43723|issue:45479", + "issue:44442|issue:45803", + "issue:43761|issue:44188", + "issue:43316|issue:43525", + "issue:44479|issue:45290", + "issue:42907|issue:45698", + "issue:44442|issue:44898", + "issue:33290|issue:34567", + "issue:42490|issue:44743", + "issue:34689|issue:43611", + "issue:33290|issue:35141", + "issue:33290|issue:34689", + "issue:43381|issue:43873", + "issue:43931|issue:45216", + "issue:43493|issue:43827", + "issue:43316|issue:45759", + "issue:44077|issue:44479", + "issue:43720|issue:44442", + "issue:41628|issue:45372", + "issue:43643|issue:44913", + "issue:43749|issue:43931", + "issue:34689|issue:36010", + "issue:43873|issue:44871", + "issue:33290|issue:36331", + "issue:44190|issue:44496", + "issue:44855|issue:45137", + "issue:43540|issue:44514", + "issue:43316|issue:44877", + "issue:42175|issue:43316", + "issue:43065|issue:44617" + ], + "prepared_review_unit_hash": "cd0c2215d24199ab904202b2c39e1bea1c174085af4b9bc89a72f227948b149a", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36328, + "estimated_input_tokens": 9082, + "estimated_eval_tokens": 18420 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is highly heterogeneous: the soft pairs mostly connect unrelated loading, config, tokenizer, vision, training, and docs bugs. No pair looks like the same underlying change or defect, so all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue: these items are not duplicates of one bug, but a grab bag of unrelated regressions and API mismatches.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good global representative because there is no one underlying problem to centralize.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Different failures: tokenizer loading in v5 vs degenerate loss in sequence classification." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Unrelated code paths: AutoTokenizer loading vs Fuyu tensor conversion error handling." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "Different subsystems: CLIPVision hidden_states regression vs attention-kernel divergence under torch.compile." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config-related, but they affect different models and bugs: Gemma3TextConfig API mismatch vs Llama4Config missing pad_token_id." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Different Qwen chat/video issues: video-input regression vs tool-call chat-template crash." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load, but one is dequantized model saving and the other is wrong custom-module loading after save_pretrained; not the same bug." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Completely different models and paths: tokenizer loading vs Perceiver image resizing/interpolation." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "Different training problems: DeepSpeed/Adafactor OOM vs TrainerState token counter not updating." + }, + { + "left": "issue:42490", + "right": "issue:44743", + "accept": false, + "reason": "Local-path import warning is unrelated to recurrent-state caching behavior in Qwen3.5." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both concern model loading, but they are distinct regressions with different root causes and model families." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "OOM with Adafactor is unrelated to embedding reinitialization in post_init." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Different bugs: optimizer memory blowup vs Llama 3.2 Vision model loading failure." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode and quantization offloading are separate execution paths." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Weight-shape mismatch on Qwen3-VL loading is unrelated to a save_pretrained checkpoint regression in Qwen3.5." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation discrepancy is unrelated to docs still referencing pipeline()." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Different config-loading problems: Gemma3TextConfig API mismatch vs not unwrapping text_config in AutoModelForCausalLM.from_config." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "PatchTST post_init validation and Qwen video-input regression are unrelated bugs." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight loading and tokenizer loading are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Different import failures: AutoImageProcessor export vs mistral_common ReasoningEffort dependency." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct reload behavior do not share the same code path." + }, + { + "left": "issue:43749", + "right": "issue:43931", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and Qwen3-VL weight mismatch are separate loading failures." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Llama model-loading regression and GenerationMixin import error are different issues." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to Gemma-3 eos_token_id config inconsistency." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed OOM and CustomTrainer compute_loss signature mismatch are distinct trainer bugs." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in an example script is unrelated to unrecognized model config loading." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 IndentationError in Deberta import is unrelated to ZeRO3 deque underflow." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Video processing in Qwen3OmniMoe and batched chat-template tool-call handling are different failures." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy and granite_speech strict-config loading are different model/config issues." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Backend packaging for TensorFlow is unrelated to Gemma3TextConfig API behavior." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video CUDA OOM are 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": 1, + "component_count": 17, + "review_unit_index": 29, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:25251", + "issue:28282", + "issue:32090", + "issue:35141", + "issue:41950", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43452", + "issue:43475", + "issue:43504", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43673", + "issue:43688", + "issue:43701", + "issue:43742", + "issue:43761", + "issue:43825", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44743", + "issue:44792", + "issue:44871", + "issue:44913", + "issue:45127", + "issue:45200", + "issue:45406", + "issue:45563", + "issue:45584", + "issue:45698" + ], + "soft_pairs": [ + "issue:25251|issue:28282", + "issue:43295|issue:43825", + "issue:43404|issue:43441", + "issue:43673|issue:44743", + "issue:44162|issue:44792", + "issue:16998|issue:22355", + "issue:43388|issue:43688", + "issue:41950|issue:43475", + "issue:44077|issue:44534", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:44871|issue:45584", + "issue:43761|issue:44479", + "issue:43295|issue:44871", + "issue:45127|issue:45200", + "issue:42617|issue:43575", + "issue:43452|issue:44496", + "issue:43575|issue:43742", + "issue:44734|issue:45406", + "issue:43646|issue:44913", + "issue:43504|issue:45698", + "issue:44617|issue:45584", + "issue:43761|issue:44242", + "issue:43931|issue:44060", + "issue:32090|issue:35141", + "issue:45563|issue:45584", + "issue:44464|issue:44871", + "issue:43065|issue:44610" + ], + "prepared_review_unit_hash": "1c4a8bc4ef0772382cba602527de0897b316460d693c4df8fdc0e99e5aad97ac", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36103, + "estimated_input_tokens": 9026, + "estimated_eval_tokens": 18308 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are mostly unrelated model/loading/training regressions, so I found no convincing duplicate cluster beyond loose subsystem similarity. The strongest representative issue is the custom-module loading regression.", + "confidence": 0.27, + "canonical_issue_reason": "issue:45698 is the clearest broad, user-facing loader regression in the set, with a concrete save/load repro and active discussion.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45698 best represents a high-impact core `from_pretrained` failure and is the most actionable issue in the group.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Different failures: pipeline output shape vs missing PyTorch import path." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Both touch processors/tokenizers, but one is a v5 regression in custom code handling while the other is just an incorrect error message for unsupported translation tasks." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Same model family, but different bugs: weight tying vs FlashAttention failure." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both are cache-related, but they affect different mechanisms and code paths (chunked prefill cache vs recurrent state reset)." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "Completely different domains: ESM2 model breakage vs Janus image generation test failure." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "Unrelated: max length handling for DeBERTa vs missing `transformers.onnx` module." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Training-related, but one is metric gathering on last batch and the other is auxiliary-loss normalization." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Both involve vision/video models, but the bugs are different: processor selection vs missing attribute in SAM3 video output." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "One is a model class API constraint; the other is a v5 buffer-initialization regression." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "Unrelated: torch.compile SDPA OOM vs checkpoint key mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "Different issues: CPU offload device mismatch vs resume checkpoint key mismatch." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Both mention tokenization/generation, but one is an eos_token_id config mismatch and the other is an empty-transcription generation crash." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "Different model families and failure modes: CLIP hidden_states regression vs Qwen video-input regression." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Processor/tokenizer regression vs eos_token_id inconsistency; not the same underlying bug." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "Both are model config/training issues, but one is LoRA/embedding collapse after merge and the other is a missing default for `mm_token_type_ids`." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "Different symptoms and paths: running a 3D script vs OOM when loading a specific model with tensor parallelism." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Both involve loading, but one is a `gguf_file` path bug and the other is an unrecognized custom model/config issue." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Different model-loading problems: OOM on large Qwen with tp vs key error for MobileLLM-125M." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "Both are service/runtime crashes, but they stem from different serve code paths and different root causes." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Custom model init breakage is unrelated to GPTNeoX config reload losing `rotary_pct`." + }, + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "Both concern loading/saving, but one is a legacy field in BEiT preset loading and the other is wrong custom-module resolution after save/load." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Unrelated: CUDA OOM in SAM3 video vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Different training/inference bugs: CLIP hidden_states regression vs missing load-balancing loss." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Related to Qwen3-VL/Next, but one is a shape mismatch on load and the other is a tied-weights warning bug." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Different failures: distributed broadcast NoneType vs output embedding reinitialization after resizing token embeddings." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Paged generation warning bug vs Whisper align_special_tokens crash; not the same issue." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward is unrelated to eos_token_id config mismatch." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Both are vision model issues, but one is a dummy Conv2d in SAM3 pixel decoder and the other is a processor/model image-size mismatch." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 30, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:35141", + "issue:41720", + "issue:42490", + "issue:43335", + "issue:43388", + "issue:43540", + "issue:43550", + "issue:43582", + "issue:43644", + "issue:43650", + "issue:43827", + "issue:43906", + "issue:43976", + "issue:43994", + "issue:44077", + "issue:44079", + "issue:44112", + "issue:44190", + "issue:44220", + "issue:44462", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44521", + "issue:44534", + "issue:44734", + "issue:44737", + "issue:44792", + "issue:44855", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45276", + "issue:45290", + "issue:45357", + "issue:45362", + "issue:45381", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45803", + "issue:45907" + ], + "soft_pairs": [ + "issue:44792|issue:44977", + "issue:44479|issue:44734", + "issue:44521|issue:45381", + "issue:43827|issue:43994", + "issue:44464|issue:45563", + "issue:44534|issue:44913", + "issue:43906|issue:45290", + "issue:44190|issue:44964", + "issue:44933|issue:45362", + "issue:41720|issue:45245", + "issue:44792|issue:45600", + "issue:44855|issue:45588", + "issue:35141|issue:42490", + "issue:43388|issue:43582", + "issue:45127|issue:45357", + "issue:44737|issue:45803", + "issue:44462|issue:45907", + "issue:43335|issue:44855", + "issue:44077|issue:44079", + "issue:44938|issue:45542", + "issue:43644|issue:44913", + "issue:43550|issue:44190", + "issue:43976|issue:44855", + "issue:43540|issue:44734", + "issue:44112|issue:45600", + "issue:44496|issue:45803", + "issue:43335|issue:44190", + "issue:43650|issue:44220", + "issue:45276|issue:45584" + ], + "prepared_review_unit_hash": "691a63f3334cc7339cda6012cef477e06f4f82a59d60f039980072dc8263cea5", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36467, + "estimated_input_tokens": 9117, + "estimated_eval_tokens": 18490 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All proposed soft edges look like loose topic/keyword similarity, not the same underlying bug or change. I would reject every candidate pair; the set is heterogeneous and there is no clear canonical issue/PR for the whole group.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Different failures in different models: Janus image generation test vs Qwen3.5 flash-attention behavior." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Both involve generation/runtime bugs, but one is a Qwen VL video regression and the other is KV-cache indexing in serve; not the same code path." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal/chat-template issues, but one is assistant masks for multimodal inputs and the other is Qwen2.5-VL vision \u0564\u056b\u0580 ids; distinct bugs." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs referencing removed pipeline() APIs is unrelated to a bad AutoModel/pipeline inference result." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Chunked compiled generation inconsistency is unrelated to a stale warning in paged generate()." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer initialization and GPTNeoX config reload defaults are different problems." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "Insufficient evidence that the isolated reproduction matches the tool-call crash; only a generic chat-template similarity is visible." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "A local dataset loading issue is unrelated to loading a multimodal model." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing/nonexistent import from image_utils is unrelated to a Qwen3.5 chat crash." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "CUDA assert with auto device mapping has nothing to do with the category-count limit error." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Janus test failure and stale auto_mappings references are unrelated." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 import/torch.jit parsing issue is unrelated to flash_attention crashing on s_aux=None." + }, + { + "left": "issue:35141", + "right": "issue:42490", + "accept": false, + "reason": "Embedding resize/post_init reinit bug is unrelated to loading local model paths with trailing slashes." + }, + { + "left": "issue:43388", + "right": "issue:43582", + "accept": false, + "reason": "Metric label handling bug is unrelated to an Apple Silicon allocator warmup TypeError." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge with extended vocabulary on tied embeddings is unrelated to incorrect visual encoder keys during save_pretrained." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "CPU device placement bug in XLNet is unrelated to a bare-except error swallowing interrupts in Fuyu conversion." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer resolution from repository files is unrelated to list_repo_files failing to forward revision." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "Sparse layer creation in SwitchTransformers is unrelated to DebertaV2 import parsing on Python 3.13." + }, + { + "left": "issue:44077", + "right": "issue:44079", + "accept": false, + "reason": "These are both model-output/config related, but they describe different bugs: optional post_init handling vs key assignment when previously None." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Python 3.14 import failure is unrelated to the TensorFlow-backend warning from tensorboard-only installs." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Junk non-persistent buffers and GPTNeoX rotary_pct reload regression are not the same issue." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to loading a local dataset script." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Python version compatibility issue is unrelated to a specific DebertaV2 import parser error." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Qwen3OmniMoe video-input ValueError is unrelated to serve KV-cache continuation tensor indexing." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "GraniteSpeech CI test flake is unrelated to stale Sam3LiteText auto-mapping references." + }, + { + "left": "issue:44496", + "right": "issue:45803", + "accept": false, + "reason": "Model config missing model_type is unrelated to Fuyu's broad exception handling." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "Sparse-layer config bug is unrelated to local dataset loading." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "Placeholder issue title is unrelated to _torch_extract_fbank_features()." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 resize_token_embeddings behavior and Whisper empty-transcription failure are different code paths and symptoms." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 31, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:39692", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:42490", + "issue:42907", + "issue:43065", + "issue:43295", + "issue:43404", + "issue:43441", + "issue:43479", + "issue:43531", + "issue:43643", + "issue:43673", + "issue:43824", + "issue:43854", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44279", + "issue:44336", + "issue:44466", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44913", + "issue:44933", + "issue:44964", + "issue:44987", + "issue:45003", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45335", + "issue:45375", + "issue:45446", + "issue:45584", + "issue:45600", + "issue:45632" + ], + "soft_pairs": [ + "issue:39692|issue:44190", + "issue:45245|issue:45584", + "issue:41950|issue:44016", + "issue:43295|issue:45276", + "issue:43479|issue:45375", + "issue:36246|issue:41628", + "issue:36246|issue:38617", + "issue:38175|issue:43065", + "issue:44186|issue:44734", + "issue:42175|issue:44279", + "issue:44683|issue:45446", + "issue:44016|issue:44220", + "issue:44466|issue:44913", + "issue:43404|issue:45216", + "issue:44246|issue:45003", + "issue:44734|issue:45632", + "issue:44561|issue:45632", + "issue:42490|issue:45632", + "issue:43643|issue:44496", + "issue:44964|issue:45600", + "issue:44112|issue:44964", + "issue:43854|issue:44964", + "issue:42907|issue:43441", + "issue:43976|issue:44987", + "issue:44016|issue:44062", + "issue:43295|issue:45335", + "issue:43673|issue:44336", + "issue:43531|issue:45600", + "issue:43824|issue:44933" + ], + "prepared_review_unit_hash": "6b7c6a00d477b5a48013c4fc9b2d8b1f0049a99d4cea74e0b9297402eceed074", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36414, + "estimated_input_tokens": 9104, + "estimated_eval_tokens": 18464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of Transformers issues, mostly import/load regressions, model/config mismatches, and a few unrelated tokenizer, docs, and serving bugs. The soft-similarity pairs are not strong duplicates; they usually share a subsystem or theme, not the same underlying defect.", + "confidence": 0.89, + "canonical_issue_reason": "issue:44964 is the clearest, most reproducible bug report in the set: a specific model load failure against latest Transformers with a concrete target and narrow scope.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44964 is the best representative issue for this cluster because it is concrete, actionable, and centered on a single user-visible regression rather than a broad or ambiguous symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39692", + "right": "issue:44190", + "accept": false, + "reason": "Different problems: notebook/example errors vs local dataset loading failure in a training script." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Unrelated bugs: category-count limit vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Different artifacts and failures: pipeline processor lookup vs notebook syntax error." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Both involve model APIs, but one is a processor/tokenizer regression and the other is embedding resize not propagating." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Different config bugs affecting different multimodal models and different fields." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and different code paths." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Distinct missing-import failures in unrelated modules." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Unrelated model behavior bug vs pixel decoder implementation issue." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Different tokenizer/NER crash vs serving KV-cache tensor indexing crash." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Generic dependency/install complaint is not the same as a missing TensorFlow backend in the torch extra." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Related area, but different concrete failures: compiled flex_attention on new torch vs an incorrect version check for AuxRequest import." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error and audio feature extraction bug are unrelated." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Weight-serialization/tieing regression is separate from GPTNeoX rotary_pct reload behavior." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Different models and different save/tie semantics; not the same underlying bug." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import slowness and unsafe sys.modules access are not the same defect." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serving KV-cache crash and trust_remote_code cache-path collision are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Both mention trust_remote_code, but one is a missing helper removal breakage and the other is a cache-path collision." + }, + { + "left": "issue:42490", + "right": "issue:45632", + "accept": false, + "reason": "Both concern local-path handling, but one is a warning on trailing slashes and the other is a leaf-directory cache collision." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading is different from an unrecognized model/config error." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Model load failure for Phi-4-multimodal-instruct is not the same as stale auto_mappings references breaking CI." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI test flake in GraniteSpeech is unrelated to model loading for Phi-4-multimodal-instruct." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Both are model load reports, but they concern different models and likely different root causes." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Dequantized save failure and FlashAttention failure in Ministral are distinct issues." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Version/platform compatibility issue is not the same as failing to load a specific model." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and tokenization API TypeError are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Different regression targets: processor/tokenizer behavior vs decoder embedding resize propagation." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache regression and ANSI formatting in loading_report are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Sliding-window model bug and stale auto_mappings references are different code paths." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but one is a missing top-level export and the other is a nonexistent image_utils import." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 32, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41950", + "issue:43295", + "issue:43299", + "issue:43335", + "issue:43381", + "issue:43450", + "issue:43479", + "issue:43525", + "issue:43526", + "issue:43577", + "issue:43650", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44075", + "issue:44242", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44351", + "issue:44368", + "issue:44462", + "issue:44496", + "issue:44521", + "issue:44617", + "issue:44683", + "issue:44779", + "issue:45020", + "issue:45042", + "issue:45081", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45325", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45542", + "issue:45584", + "issue:45593", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:45907" + ], + "soft_pairs": [ + "issue:44496|issue:45042", + "issue:43526|issue:43901", + "issue:43299|issue:45216", + "issue:43335|issue:45593", + "issue:44075|issue:44368", + "issue:45335|issue:45584", + "issue:43976|issue:44279", + "issue:43381|issue:45593", + "issue:43901|issue:44496", + "issue:43299|issue:45357", + "issue:44496|issue:45759", + "issue:44521|issue:45325", + "issue:41950|issue:45020", + "issue:44351|issue:45278", + "issue:44242|issue:45200", + "issue:43976|issue:45405", + "issue:43479|issue:43525", + "issue:44779|issue:45812", + "issue:41950|issue:45823", + "issue:38175|issue:44617", + "issue:44683|issue:45542", + "issue:43577|issue:45216", + "issue:39692|issue:43901", + "issue:44279|issue:45405", + "issue:43299|issue:43854", + "issue:43295|issue:44779", + "issue:41950|issue:43650", + "issue:44462|issue:45081", + "issue:45081|issue:45907", + "issue:44297|issue:44462", + "issue:44016|issue:44291", + "issue:43450|issue:44279" + ], + "prepared_review_unit_hash": "ebb1fbfbaded5448d5f51f4780313240f3907517830fc4ed4be167d727ab072f", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36853, + "estimated_input_tokens": 9214, + "estimated_eval_tokens": 18684 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are separate bugs across tokenizers, processors, configs, and model-loading paths. I don\u2019t see any soft pair that clearly describes the same underlying defect, so I rejected them all. The closest umbrella issue is the broad AutoTokenizer/tokenizer-loading regression, but even that is not a true duplicate anchor for the rest.", + "confidence": 0.67, + "canonical_issue_reason": "issue:44462 is the broadest tokenizer-loading regression in the set and has the most obvious overlap with the other tokenizer-related reports, but the cluster is still not a single duplicate bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the best representative issue because it is broad, user-facing, and sits near several tokenizer-related reports, making it the most plausible triage anchor despite the lack of true duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Different bugs: model config recognition vs PIL image processor torchvision dependency." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BeitImageProcessorFast label handling is unrelated to a docs/behavior mismatch for TextClassificationPipeline." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Qwen3VL loading regression and Qwen3.5 save_pretrained regression are different code paths." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "Sparse-layer initialization and D-FINE auxiliary-loss logic are unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "SGD argument handling is unrelated to a tie_word_embeddings warning." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize propagation and Whisper empty-transcription handling are different problems." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "Python-version compatibility and a generic dependency issue are not the same defect." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to D-FINE denoising/aux-loss behavior." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs drift for return_all_scores does not match AutoTokenizer ignoring tokenizer.json." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both mention Qwen3.5, but one is model loading and the other is incorrect visual-encoder checkpoint keys." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "AutoTokenizer repository-file handling and composite config unwrapping are different bugs." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Multimodal assistant masks and Qwen2.5-VL rope indexing are distinct code paths." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification processor lookup is unrelated to remote_code model breakage." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "A specific HybridCache import error is not the same as a broad import-errors-after-upgrade report." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Load-balancing loss routing and Gemma 4 mm_token_type_ids defaults are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python support regression and a PEFT minimum-version bump are different issues." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Multimodal config default initialization and missing pad_token_id are not the same bug." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and likely different code paths." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Video processor lookup and Gemma4 PLE device placement are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "Zero probabilities for SigLIP2 and a Sam3Video OOM are clearly different failures." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "flex_attention compilation on torch 2.9 is unrelated to TensorBoard/TensorFlow backend installation." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint serialization are different model-loading bugs." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "SigLIP2 doc example errors are not the same as a TextClassificationPipeline docs mismatch." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A dependency problem is not the same as bumping MIN_PEFT_VERSION too early." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3VL loading regression and GLM-4.7-Flash test loading are unrelated model-specific issues." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Custom processor.tokenizer breakage is not the same as Deepseek tokenizer output regressions." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "Video pipeline processor lookup and a placeholder issue title are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Ignoring tokenizer.json and a Mistral regex patch crash are different tokenizer bugs." + }, + { + "left": "issue:45081", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer regex patch failure is unrelated to list_repo_files revision forwarding." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer_class metadata mismatch and ignoring tokenizer.json are distinct save/load issues." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batching shape is unrelated to a dependency issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 33, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:33290", + "issue:42175", + "issue:42994", + "issue:43065", + "issue:43122", + "issue:43262", + "issue:43317", + "issue:43441", + "issue:43525", + "issue:43643", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43784", + "issue:43824", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44188", + "issue:44261", + "issue:44263", + "issue:44297", + "issue:44336", + "issue:44361", + "issue:44466", + "issue:44521", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44898", + "issue:44987", + "issue:45276", + "issue:45290", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45656", + "issue:45712", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:33290|issue:45656", + "issue:43441|issue:45834", + "issue:45600|issue:45712", + "issue:43065|issue:44898", + "issue:42994|issue:43317", + "issue:44466|issue:45276", + "issue:44261|issue:44263", + "issue:44623|issue:45397", + "issue:43650|issue:45290", + "issue:44623|issue:44749", + "issue:43441|issue:44683", + "issue:43653|issue:45593", + "issue:43262|issue:44521", + "issue:43723|issue:44162", + "issue:44016|issue:45823", + "issue:43673|issue:43761", + "issue:42175|issue:43976", + "issue:44361|issue:45593", + "issue:44671|issue:44779", + "issue:43784|issue:45542", + "issue:43901|issue:43994", + "issue:44987|issue:45542", + "issue:43122|issue:43650", + "issue:44297|issue:45397", + "issue:43824|issue:43976", + "issue:44188|issue:44336", + "issue:43525|issue:43881", + "issue:43525|issue:43643" + ], + "prepared_review_unit_hash": "e4edceb586338d007116c60bb541d9de33c8eeebe712c9c4195fd7ff3f24e42c", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35964, + "estimated_input_tokens": 8991, + "estimated_eval_tokens": 18238 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are largely unrelated Transformers issues. The soft-pair candidates mostly share broad vocabulary (e.g. deepspeed, apply_chat_template, loading, tokenizer) but do not appear to be the same concrete bug or change, so I reject all soft edges.", + "confidence": 0.89, + "canonical_issue_reason": "issue:44521 is the broadest and most referenced issue in the set, so it is the best available anchor if one must be chosen, though the collection is not a true duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 has the widest scope and strongest discussion/inbound-reference signal, making it the most representative issue among otherwise unrelated reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "Both involve deepspeed/optimizer behavior, but one is OOM during Adafactor use and the other is double optimizer stepping; different concrete failures." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "Unrelated bugs: FlashAttention failure for Ministral-3 vs long OCR index error in Kosmos2.5." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both touch generated/dummy mappings, but one is stale Sam3LiteText references and the other is leftover dummy classes; different fixes." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Different models and symptoms: dummy Conv2d in Sam3PixelDecoder vs Perceiver resolution/interpolation failure." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized model saving failure and dequantized-model offload loading failure are separate code paths." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "One is device-dependent lm_head serialization, the other is resize_token_embeddings not updating Gemma4 embedding/output layers." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "Different model internals: MLA layernorm epsilon precision issue vs torch.split return handling in GlmMoeDsaIndexer." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing files on processor.save_pretrained is not the same as ZeRO3 from_pretrained failure for gemma-4." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "The first is a vague data request; the second is a specific apply_chat_template crash with tool-call assistant messages." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "processor.save_pretrained file omission and Chinese performance regression after upgrade are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Both mention attention/flash, but the failures are on different models and different triggers." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "Tokenizer special-token registration bug and D-FINE auxiliary-loss logic are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both concern apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant_mask generation." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer loading regression and ESM2 model breakage are different issues." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error is unrelated to Gemma4 device-mismatch during forward." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Generation cache missing in chunked_prefill and CLIPVisionModel hidden_states regression are separate bugs." + }, + { + "left": "issue:42175", + "right": "issue:43976", + "accept": false, + "reason": "Packaging/backend omission is not the same as a Python-version compatibility failure." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer AttributeError and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "Both are model/tokenizer regressions in v5, but the affected models and failure modes differ." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Importing sentence-transformers fails due to missing nn; the other is a TensorFlow backend packaging issue." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to incorrect SigLIP2 inference results." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Loading a specific model on transformers>=5.1.0 and tensorboard-only TensorFlow backend issues are different." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenization behavior change and a vague 'ADD THE DATA' request do not describe the same bug." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch is unrelated to gemma-4 ZeRO3 loading." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Missing Qwen2.5-VL export and Python 3.9/3.10 compatibility are unrelated." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Attention-kernel divergence under torch.compile is unrelated to ANSI code emission in loading_report." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Llama4Config missing pad_token_id and glm-4v-9b load failure are different model-specific issues." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "A missing config attribute in Llama4Config is not the same as trust_remote_code dropping fields from AutoConfig." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 34, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:43232", + "issue:43299", + "issue:43352", + "issue:43450", + "issue:43526", + "issue:43531", + "issue:43596", + "issue:43673", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44373", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44589", + "issue:44617", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:44987", + "issue:45003", + "issue:45200", + "issue:45250", + "issue:45292", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45593", + "issue:45701" + ], + "soft_pairs": [ + "issue:43450|issue:44617", + "issue:44589|issue:45362", + "issue:41628|issue:43976", + "issue:43901|issue:44246", + "issue:44336|issue:44373", + "issue:45561|issue:45563", + "issue:42491|issue:43299", + "issue:44242|issue:45593", + "issue:44295|issue:45397", + "issue:41950|issue:44220", + "issue:44246|issue:44496", + "issue:43531|issue:45362", + "issue:43352|issue:45250", + "issue:44336|issue:44485", + "issue:36246|issue:42757", + "issue:43526|issue:45003", + "issue:36246|issue:44351", + "issue:45003|issue:45561", + "issue:43673|issue:44561", + "issue:44246|issue:44871", + "issue:44242|issue:44857", + "issue:44295|issue:44749", + "issue:44162|issue:45200", + "issue:36246|issue:43596", + "issue:44779|issue:45292", + "issue:44877|issue:45375", + "issue:45292|issue:45584", + "issue:43901|issue:45003", + "issue:45292|issue:45701", + "issue:43232|issue:44336", + "issue:44496|issue:45003", + "issue:44987|issue:45459" + ], + "prepared_review_unit_hash": "0f1dc857b05fe3a4cf5f0842988a3941516c9115db91c2dbcc3e317afb77295e", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36335, + "estimated_input_tokens": 9084, + "estimated_eval_tokens": 18424 + }, + "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 regressions (imports, model-specific loading, generation, docs, testing, and performance). Only one soft pair looks like a plausible duplicate; the rest are too different in code path or failure mode to merge.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 44877 is the clearest concrete bug in the cluster and the best representative of the only strong overlap: strict config handling dropping required model fields during loading.", + "canonical_pr_reason": null, + "best_issue_reason": "44877 is the most suitable single issue to anchor the cluster because it matches the same strict-config code path as the only plausible duplicate candidate and is more specific than the broader version-breakage reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Different bugs: pipeline processor selection vs CUDA OOM in Sam3Video." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "One is a storage/type import failure; the other is a Qwen chat/runtime crash." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Import export regression vs Python-version compatibility issue; not the same bug." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs mismatch vs a MoE load-balancing loss bug in training." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "Different scopes: terminal ANSI output vs a wrong docstring." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "Test race condition vs a stale generation warning; unrelated code paths." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen/MoE, but one is LoRA compatibility across versions and the other is a model-loading failure." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Similar symptom shape, but different models and loss mechanisms." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "Buffer registration error vs ZeRO-3 from_pretrained loading problem." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video pipeline processor lookup vs audio feature extraction; unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import performance issue vs unrecognized model/config loading failure." + }, + { + "left": "issue:43531", + "right": "issue:45362", + "accept": false, + "reason": "Both Qwen-related, but sliding_window handling and chat crashes are different problems." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Specific model/Flash-Attn incompatibility vs a generic Flash Attention topic." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI-report formatting vs GLM-5 RoPE implementation; no overlap." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols and modules." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "Image-processor label reduction bug vs unsafe sys.modules access; unrelated." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing exports from different parts of the package." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Import/module safety bug vs a test file race condition." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Both are v5 regressions, but generation cache and trust_remote_code import removal are different code paths." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import slowdown vs Gemma eos_token_id config mismatch." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Different failures: missing auxiliary loss vs AMP/CUDA crash." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Position_ids buffer error vs a data-filtering performance regression." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "Different models and different bugs; not mergeable." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Import symbol issue vs DeepSpeed zero3/BertModel indexing error." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer output regression vs embedding-resize synchronization bug." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": true, + "reason": "Both point to the same strict-config code path dropping required fields from model configs." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize bug vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs issue vs unsafe module lookup; no common underlying bug." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Resize-embeddings behavior vs version-dependent tokenization changes." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs bug vs terminal ANSI output bug." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Config/model recognition vs sys.modules access safety." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure vs tokenizer exception masking; different layers." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The summary matches the packet\u2019s titles and the one accepted soft pair (44877/45375) is the only clearly defensible overlap: both are strict-config omissions in model config loading. The other rejections stay appropriately cautious and do not overclaim duplicate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 35, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:42886", + "issue:42994", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43475", + "issue:43482", + "issue:43540", + "issue:43646", + "issue:43653", + "issue:43673", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44246", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44466", + "issue:44623", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:44977", + "issue:44995", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45230", + "issue:45278", + "issue:45310", + "issue:45335", + "issue:45356", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45563", + "issue:45588", + "issue:45600", + "issue:45656", + "issue:45759" + ], + "soft_pairs": [ + "issue:43065|issue:43408", + "issue:45375|issue:45759", + "issue:42886|issue:45229", + "issue:43262|issue:44246", + "issue:43257|issue:45137", + "issue:44995|issue:45200", + "issue:43475|issue:43540", + "issue:44060|issue:44077", + "issue:45397|issue:45656", + "issue:43653|issue:44162", + "issue:44466|issue:45335", + "issue:44995|issue:45588", + "issue:44368|issue:45563", + "issue:44368|issue:44977", + "issue:43673|issue:44734", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:44933|issue:45459", + "issue:44869|issue:45356", + "issue:44297|issue:44623", + "issue:43232|issue:43673", + "issue:44361|issue:44749", + "issue:43646|issue:44162", + "issue:43673|issue:45278", + "issue:44623|issue:45656", + "issue:44749|issue:45656", + "issue:44749|issue:45310", + "issue:42994|issue:43482", + "issue:45230|issue:45397", + "issue:28282|issue:30990" + ], + "prepared_review_unit_hash": "809bad2185657622bcbcf4e78bac2cf52e89f42376d6bf7ee7ef8e005a9f1a7a", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36006, + "estimated_input_tokens": 9002, + "estimated_eval_tokens": 18260 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is very heterogeneous: it mixes unrelated tokenizer, generation, model-loading, DeepSpeed, SAM3, Gemma, Qwen, and save/load bugs. I do not see any soft pair that is clearly the same underlying issue; all should stay separate. The broadest representative is the generic v5 regression/import report, but it still does not meaningfully cover the rest.", + "confidence": 0.9, + "canonical_issue_reason": "issue:45278 is the most umbrella-like report (\u201cmany import errors after update\u2026\u201d), so it is the closest thing to a cluster representative, even though the cluster itself is too mixed to have a truly good canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the broadest issue in the set and the closest fit for a representative cluster label.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Both are SAM3-related, but one is about a dummy Conv2d in the pixel decoder and the other is a model-type warning for sam3_video vs sam3_tracker; different bugs." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal config handling, but one is about a missing config field being dropped and the other is about AutoModelForCausalLM.from_config not unwrapping text_config; not the same fix." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline tokenizer cache loading and Gemma4 multi-GPU CUDA OOM are unrelated problems." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sample-rate defaulting and slow import behavior are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Both mention DeepSpeed, but one is Qwen3 MoE weight conversion during loading and the other is a ZeRO3 deque error; different code paths." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "GlmMoeDsa stale indexer cache on second forward pass is unrelated to Gemma4 mm_token_type_ids defaults." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Different model families and failures: SAM3 video output attribute error vs Qwen3OmniMoe video-processing ValueError." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Qwen3-Next tied-weights warning and patchtsmixer post_init allowance are unrelated." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma-4 Zero3 from_pretrained failure and a duplicated optimizer step under DeepSpeed are different bugs." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and ESM2 being broken are not the same underlying issue." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both concern tied-embedding behavior, but one is serialization of lm_head.weight and the other is resize_token_embeddings not updating decoder.embed_tokens; different concrete failures." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale indexer cache crash in GlmMoeDsa and flash-attention s_aux=None AttributeError are unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "A tied-word-embeddings warning for Qwen3.5 fine-tuning is unrelated to a stale num_return_sequences warning in paged generate()." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Both involve Qwen3.5, but one is a configuration warning and the other is a flash-attention generation failure; not the same bug." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Chunked-prefill cache missing and /v1/responses KV-cache continuation indexing are different generation bugs." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error and removed Sam3LiteText config references are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and a tied-embeddings warning are unrelated." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Missing image_utils import and hidden tokenizer decode errors when protobuf is absent are different import-path issues." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper timestamp decode crash and Kimi-K2.5 tokenizer regression are distinct tokenizer/decoding problems." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Tokenizer save_pretrained writing the wrong tokenizer_class and processor.save_pretrained missing files are related to saving, but not the same concrete bug." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both are generation/cache-related, but one is sync_gpus kwarg updating and the other is chunked_prefill cache availability; different fixes." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and a slowdown after upgrading transformers are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Generic custom model initialization breakage and ESM2-specific failure are not the same issue." + }, + { + "left": "issue:43673", + "right": "issue:45278", + "accept": false, + "reason": "Generation cache missing during chunked_prefill is unrelated to broad import errors after upgrading." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Processor save_pretrained missing files and duplicated DeepSpeed optimizer steps are unrelated." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "A performance regression after upgrading transformers and a duplicated optimizer step under DeepSpeed are different problems." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3.5, but one is a slowdown report and the other is a from_pretrained error with newer transformers; not the same bug." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure and GGUF loading failure are opposite-direction serialization/loading issues, not one bug." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "'Bug report' is too vague to match concretely, and the Gemma-4 Zero3 from_pretrained issue is specific; no evidence they are the same." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "PyTorch missing ImportError for AutoModel and Sentence Transformers hanging on load 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": 1, + "component_count": 17, + "review_unit_index": 36, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:30990", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43377", + "issue:43475", + "issue:43504", + "issue:43525", + "issue:43526", + "issue:43643", + "issue:43673", + "issue:43704", + "issue:43824", + "issue:43873", + "issue:43976", + "issue:44038", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44661", + "issue:44792", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45375", + "issue:45381", + "issue:45478", + "issue:45561", + "issue:45712", + "issue:45753" + ], + "soft_pairs": [ + "issue:42371|issue:45092", + "issue:44038|issue:44623", + "issue:43475|issue:43643", + "issue:43475|issue:45381", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:42994|issue:43525", + "issue:43475|issue:44661", + "issue:45375|issue:45478", + "issue:43232|issue:44188", + "issue:45310|issue:45375", + "issue:43873|issue:44945", + "issue:42673|issue:43704", + "issue:41628|issue:44351", + "issue:42831|issue:44222", + "issue:44945|issue:45753", + "issue:44222|issue:45310", + "issue:43673|issue:44188", + "issue:42994|issue:43824", + "issue:36010|issue:41628", + "issue:42175|issue:45712", + "issue:42222|issue:45200", + "issue:43232|issue:44792", + "issue:44038|issue:45310", + "issue:43377|issue:44242", + "issue:44496|issue:45561", + "issue:43526|issue:45561", + "issue:44964|issue:45137", + "issue:43504|issue:45561", + "issue:42175|issue:44933", + "issue:42898|issue:44568", + "issue:30990|issue:35141", + "issue:43976|issue:44933" + ], + "prepared_review_unit_hash": "3b998233c90728c6da1a1f9e68dcd9999ecc9c70280b305f2a287fe320c166b5", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37473, + "estimated_input_tokens": 9369, + "estimated_eval_tokens": 18994 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster remains heterogeneous, but there is at least one exact-duplicate issue pair that should be accepted: issue:45310 and issue:45478 share the same title and symptom, so they look like the same report. The rest of the soft edges are still mostly broad-similarity matches across different bugs, models, or subsystems.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue for the whole cluster: it still spans many unrelated bug reports, even though issue:45310 and issue:45478 are an exact duplicate pair and issue:42673/issue:43704 is another duplicate pocket.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue: the cluster is too mixed to be represented by one issue, despite the presence of a few duplicate pairs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 behavior warning vs old InternVL2 meta-init incompatibility; different failure modes." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe from_pretrained bug vs missing processor save files; only broad model/processor overlap." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "SAM3 missing attribute vs trust_remote_code dropping config fields; different bugs and code paths." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "SAM3 output attribute error vs qwen2.5-vl video position-id bug; different models and root causes." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but they involve different symbols and different underlying export/import problems." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Mistral tokenizer regex crash vs auto-docstring annotation crash; unrelated subsystems." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized save failure vs missing pad_token_id on Llama4Config; different root causes." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "SAM3 attribute bug vs tokenizer-mapping registration failure; not the same underlying issue." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Related Qwen3.5 MoE area, but the concrete bugs differ: missing deepstack_visual_indexes vs from_pretrained error." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation kwargs update after sync_gpus vs attention-kernel divergence under torch.compile; different code paths." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Qwen3.5 MoE from_pretrained error vs missing deepstack_visual_indexes in vision config; not the same fix." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization/offloading behavior vs incorrect pipeline-parallel LLM output; too broad and different." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact same title and symptom: Qwen3ForCausalLM VRAM leak with multiple dataloader threads." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Different import errors for different symbols (`AutoImageProcessor` vs `HybridCache`)." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "FP8 accuracy issue vs FP8 save_pretrained problem; same area, but not the same bug." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Incorrect output under pipeline parallelism vs an infinite loop for one image; different symptoms and triggers." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "FP8 save_pretrained on MoE vs Qwen3.5 MoE from_pretrained error; different concrete failures." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Generation cache missing in v5 chunked prefill vs attention-kernel branching bug; unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Quantized save failure vs missing Qwen2_5_VLForConditionalGeneration import; different issues." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Missing GenerationMixin import vs missing AutoImageProcessor import; both are import regressions, but unrelated." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "TensorFlow backend packaging issue vs leftover dummy PT classes leaking into dir(transformers); different packaging problems." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Broken ViTPose models vs Gemma 4 token-type-id defaulting; unrelated model families." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs/cache issue vs janus image-generation test failure; no clear shared root cause." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Qwen3-VL-Moe bug vs Qwen3.5 MoE from_pretrained error; same family, but not the same concrete bug." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "MIMI encoder batching/padding-mask bug vs load-balancing loss omission in MoE; unrelated behavior." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrecognized model/config issue vs xdist race in testing utils; totally different layers." + }, + { + "left": "issue:43526", + "right": "issue:45561", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs xdist race in testing utils; unrelated." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Phi-4 multimodal load failure vs DeepSpeed ZeRO3 deque underflow; different subsystems." + }, + { + "left": "issue:43504", + "right": "issue:45561", + "accept": false, + "reason": "BEiT pretrained preset load bug vs xdist race in testing utils; unrelated." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "TensorFlow packaging vs missing image_utils import; not the same bug." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "v5 tokenization cleanup behavior change vs BOS/EOS not added for mdeberta tokenizer; related area, different issue." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence Transformers load hang vs embedding reinit after resizing token embeddings; completely different bugs." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version compatibility bug vs missing image_utils import; unrelated." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Identical titles and same reported Qwen3.5 MoE from_pretrained error; this is an exact duplicate pair." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster-homogeneity summary is fine, but the soft-edge judgments are not fully conservative. In particular, issue:45310 and issue:45478 have identical titles (`[BUG] transformers>=5.4.0, Qwen3.5 Moe from_pretrained error`), so treating that pair as non-duplicate is too strict given the packet. Because of that missed exact duplicate pair, I can\u2019t accept the output as-is." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 37, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30333", + "issue:33290", + "issue:34689", + "issue:36331", + "issue:41628", + "issue:42757", + "issue:42831", + "issue:42898", + "issue:43116", + "issue:43232", + "issue:43278", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:44060", + "issue:44079", + "issue:44188", + "issue:44190", + "issue:44206", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44448", + "issue:44484", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44869", + "issue:44933", + "issue:44977", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45310", + "issue:45356", + "issue:45405", + "issue:45656", + "issue:45712", + "issue:45812", + "issue:45834" + ], + "soft_pairs": [ + "issue:43479|issue:44869", + "issue:43479|issue:44079", + "issue:44623|issue:45310", + "issue:43784|issue:43824", + "issue:44188|issue:44373", + "issue:43278|issue:45137", + "issue:42898|issue:45812", + "issue:44734|issue:45103", + "issue:30333|issue:33290", + "issue:43723|issue:44568", + "issue:43874|issue:45092", + "issue:42898|issue:45356", + "issue:44060|issue:45125", + "issue:42898|issue:44779", + "issue:45405|issue:45712", + "issue:44295|issue:45656", + "issue:42898|issue:44448", + "issue:44933|issue:45712", + "issue:44222|issue:44297", + "issue:44297|issue:45656", + "issue:43116|issue:44190", + "issue:43479|issue:43644", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:44206|issue:45103", + "issue:41628|issue:42757", + "issue:22355|issue:28282", + "issue:30333|issue:36331", + "issue:30333|issue:34689", + "issue:44297|issue:45310", + "issue:44222|issue:44484", + "issue:43232|issue:45834", + "issue:43723|issue:44977", + "issue:28282|issue:30333" + ], + "prepared_review_unit_hash": "0addc67cd4e93fdd756b4568460ebded52120856c34163c07488f1581a2545f0", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37872, + "estimated_input_tokens": 9468, + "estimated_eval_tokens": 19192 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs are mostly false positives: they connect unrelated import errors, tokenizer regressions, training issues, and config/model bugs that do not share the same concrete fix. No PRs are present in the cluster. The closest hub is the v5 tokenizer regression issue, but it is still only a loose representative, not a true duplicate anchor.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 42898 is the broadest hub among the soft edges and best matches the recurring v5 tokenizer-regression theme, even though most neighboring pairs are not true duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "42898 is the least narrow representative of the cluster because it sits at the center of several tokenizer-related soft links and has the strongest chance of being the intended anchor issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Different subsystems: multimodal config initialization vs Whisper timestamp decoding crash." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "One is config default handling; the other is ModelOutput key assignment logic." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Both involve saving/loading, but the concrete bugs are different processor files vs Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Different import failures in different packages and code paths." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Attention-kernel divergence under torch.compile is unrelated to a docstring typo." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Different runtime problems: dtype drift during eval vs DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they describe different concrete failures and likely different fixes." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "Serve KV-cache indexing bug is unrelated to auto-docstring annotation parsing." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on failed jobs and an Adafactor+DeepSpeed OOM are unrelated bugs." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "General tokenizer loading regression is not the same as mdeberta special-token behavior." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Different multimodal loading failures with different root causes." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and behaviors." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Tied-weights warning bug is unrelated to missing tensor-parallel plan support." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Different tokenizer regressions affecting different models and failure modes." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "Unreleased PEFT version bump is unrelated to dummy class cleanup." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Position_ids buffer access bug is unrelated to double optimizer stepping under DeepSpeed." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Both mention v4/v5 output changes, but they do not point to the same concrete defect." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Missing image_utils import and dummy-class leakage are separate API-surface issues." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "Different save_pretrained bugs: FP8 MoE serialization vs tokenizer config mismatch." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save_pretrained mismatch is unrelated to DeepSpeed optimizer stepping." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Different example scripts and different failures." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Config None-handling is unrelated to non-persistent buffer initialization." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Both are save_pretrained-related, but on different objects and different bugs." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FP8 accuracy drift is unrelated to missing processor save files." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Feature extractor argument regression is unrelated to auto-docstring annotation handling." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Two separate import errors from different modules and different missing symbols." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Different import errors caused by different missing dependencies/modules." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLflow reporting on failure is unrelated to CustomTrainer.compute_loss signature mismatch." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "Training-job reporting and Llama model loading regression are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer save_pretrained metadata bug is unrelated to Qwen3.5 MoE loading failure." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE serialization bug is unrelated to max_shard_size default behavior." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation KV-cache update bug is unrelated to long-ocr indexing in Kosmos2.5." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading regression is unrelated to flash-attention generation failure." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "AutoModel missing PyTorch and MLflow job reporting 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": 1, + "component_count": 17, + "review_unit_index": 38, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:35141", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42994", + "issue:43066", + "issue:43122", + "issue:43232", + "issue:43479", + "issue:43576", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44060", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44521", + "issue:44568", + "issue:44623", + "issue:44829", + "issue:44871", + "issue:44913", + "issue:44991", + "issue:45092", + "issue:45103", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45593", + "issue:45753", + "issue:46002" + ], + "soft_pairs": [ + "issue:30333|issue:35141", + "issue:44263|issue:45092", + "issue:44373|issue:44485", + "issue:44263|issue:44360", + "issue:44295|issue:44623", + "issue:44514|issue:45103", + "issue:44483|issue:45406", + "issue:44261|issue:45092", + "issue:43723|issue:44871", + "issue:45092|issue:45357", + "issue:43723|issue:44991", + "issue:30990|issue:38175", + "issue:44829|issue:46002", + "issue:43723|issue:44442", + "issue:41628|issue:43824", + "issue:43479|issue:44913", + "issue:42831|issue:45310", + "issue:44263|issue:44373", + "issue:39401|issue:44568", + "issue:42831|issue:44038", + "issue:42757|issue:45278", + "issue:42886|issue:42994", + "issue:43232|issue:45593", + "issue:43756|issue:44060", + "issue:43576|issue:43784", + "issue:42831|issue:45753", + "issue:42886|issue:43066", + "issue:43122|issue:44521", + "issue:42371|issue:44263" + ], + "prepared_review_unit_hash": "74dc0cbd4f74cb8381b421ddb29adac0290eeba0aa4612af7d4ab3a45fe277eb", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35590, + "estimated_input_tokens": 8898, + "estimated_eval_tokens": 18052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: mostly Transformers v5 regressions around tokenizers/imports/processors/model internals, but the soft pairs point to different concrete bugs rather than true duplicates. I would not merge any of the proposed soft edges.", + "confidence": 0.92, + "canonical_issue_reason": "No single issue is a safe canonical for the cluster: the titles describe several unrelated failure modes (tokenizer loading, import errors, multimodal processor behavior, config/init bugs, and model-specific training/inference regressions), and none of the soft pairs appear to share the same underlying code path.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43723 is the best representative issue because it is the broadest and most central tokenizer-loading regression in the set, but it still does not subsume the other reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Different subsystems and failures: MLFlow reporting on training failure vs. output embedding reinitialization after resize." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "GLM-MoE DSA indexing bug vs. remote-code meta-init incompatibility for old InternVL2 checkpoints; not the same code path." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Docstring wording issue for position_ids vs. GLM-5 RoPE implementation bug; unrelated." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both touch DSA indexing, but one is about torch.split outputs and the other about a missing ReLU; different concrete bugs." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Registering position_ids as a buffer vs. missing files in processor.save_pretrained; unrelated failures." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Batched chat_template crash with padding=False vs. auto_docstring AttributeError from future annotations; different areas." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat/completions request rejection vs. Gemma4Processor missing _tokenizer in serve; not the same bug." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "Layernorm eps precision issue in MLA vs. meta-init incompatibility for old checkpoints; unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "General tokenizer-loading regression vs. Gemma-3 eos_token_id mismatch; different symptoms and fixes." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Remote-code meta-init incompatibility vs. incorrect visual encoder keys on save_pretrained; different model lifecycle stages." + }, + { + "left": "issue:43723", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading complaints, but they target different models and failures; not the same underlying bug." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence Transformers loading hang vs. SIGLIP2 zero probabilities; unrelated model behavior." + }, + { + "left": "issue:44829", + "right": "issue:46002", + "accept": false, + "reason": "FlashAttention-3 training degeneration vs. NaNs after checkout/init in classification heads; different failure modes." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "AutoTokenizer load regression vs. FastSpeech2ConformerTokenizer-specific load failure; too different to merge." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "AutoImageProcessor import failure vs. Qwen2_5_VLForConditionalGeneration import failure; separate missing symbols." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Phi4MultimodalConfig default-init bug vs. GPTNeoX rotary_pct not persisting on reload; unrelated config issues." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue vs. Qwen3.5 MoE from_pretrained error; different problems." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "DSA indexer runtime bug vs. a wrong docstring; no shared bug." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Qwen3 tokenizer offset_mapping bug vs. add_special_tokens not adding BOS/EOS for mdeberta-v3; different tokenization paths." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue vs. Qwen3-VL-Moe bug; unrelated model-specific regressions." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "Single missing is_offline_mode import vs. broad import errors after upgrade; related theme but not the same concrete bug." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Tokenizer cache/offline load failure vs. quantized model saving failure; different subsystems." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwargs update after sync_gpus vs. D-FINE auxiliary losses when denoising is off; unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Smollm3 RoPE layer count bug vs. Qwen3-Next tied-weights warning involving dt_bias; different model internals." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "transformers env CLI breakage vs. sentence-transformers import NameError; separate issues." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "FineGrainedFP8 accuracy regression vs. Qwen3_5 image-specific infinite loop; not the same bug." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline tokenizer cache loading failure vs. wrong tokenizer decoder type in v5; different tokenizer defects." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Different tokenization output across versions vs. multimodal assistant_masks all zero in apply_chat_template; not the same issue." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 API settings warning vs. GLM-MoE DSA indexer 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": 1, + "component_count": 17, + "review_unit_index": 39, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29127", + "issue:30990", + "issue:33357", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42757", + "issue:42907", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43646", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:43976", + "issue:44038", + "issue:44117", + "issue:44222", + "issue:44261", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44360", + "issue:44373", + "issue:44485", + "issue:44488", + "issue:44514", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44743", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45290", + "issue:45478", + "issue:45600", + "issue:46002" + ], + "soft_pairs": [ + "issue:44117|issue:44704", + "issue:22355|issue:28218", + "issue:43646|issue:46002", + "issue:30990|issue:33357", + "issue:44295|issue:44297", + "issue:43232|issue:44743", + "issue:44704|issue:45290", + "issue:42907|issue:44945", + "issue:43122|issue:44514", + "issue:41628|issue:45278", + "issue:43976|issue:44945", + "issue:44261|issue:44373", + "issue:43784|issue:45600", + "issue:39401|issue:44488", + "issue:42907|issue:43937", + "issue:43408|issue:43475", + "issue:44360|issue:44485", + "issue:39401|issue:44521", + "issue:43116|issue:45200", + "issue:44625|issue:44829", + "issue:44038|issue:44297", + "issue:42907|issue:44964", + "issue:29127|issue:30990", + "issue:43122|issue:44779", + "issue:44038|issue:44295", + "issue:36296|issue:43116", + "issue:42907|issue:43452", + "issue:43824|issue:44351", + "issue:44038|issue:44222", + "issue:45216|issue:45478", + "issue:42757|issue:44351" + ], + "prepared_review_unit_hash": "5dec8af14112048f5fd271ee1c5b94f6279cf3b4a6be1b9a9563bca6c315a449", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36572, + "estimated_input_tokens": 9143, + "estimated_eval_tokens": 18542 + }, + "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 across tokenization, imports, generation, multimodal models, and training/runtime regressions. The soft links are largely lexical/topic similarity rather than the same concrete bug, so I reject all soft edges.", + "confidence": 0.9, + "canonical_issue_reason": "45278 is the broadest umbrella regression in the set (multiple import errors after upgrading), so it is the best representative issue for this heterogeneous cluster, though the cluster is not a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "45278 is the most generic and representative issue here; it best summarizes the cluster\u2019s broad \u201cimport breakage after upgrade\u201d theme even if it does not match the other issues exactly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Different failure modes: tokenizer mapping fallback vs AutoProcessor kwargs not reaching cached_file. Same API surface, but not the same bug." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "One is a missing module import, the other is tokenization spacing after added tokens. No shared underlying code-path." + }, + { + "left": "issue:43646", + "right": "issue:46002", + "accept": false, + "reason": "Custom model initialization breakage and NaNs in classification heads are distinct training/runtime problems." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Both are loading-related, but one is a hang and the other is a Mac bus error with CLIP; different root causes." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Position_ids buffer access and tokenizer_class metadata mismatch are unrelated save/load behaviors." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation/cache, but one is sync_gpus bookkeeping and the other is recurrent state reset with seq_len>1." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "cached_file argument forwarding is unrelated to chat template crashes on tool-call assistant messages." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized Ministral/Devstral models and incorrect output under pipeline parallelism are different bugs." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer-version drift and apply_chat_template batching/padding failure are different tokenization paths." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Both are import errors, but 41628 is a specific missing symbol while 45278 is a broad upgrade breakage report; not the same concrete issue." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python-version compatibility and pipeline-parallel wrong output are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A model config precision bug and a wrong docstring are not the same underlying problem." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Sentence-transformers import failure and broken auto_mappings references in CI are separate breakages." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 offset_mapping errors and loading cjvt/sleng-bert are different tokenizer/model-loading issues." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Save_pretrained failure for dequantized models and invalid GenerationConfig for GLM-5 are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Both are SAM3-related, but a model-type warning and a missing output attribute are distinct bugs." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "DSA indexer activation and GLM-5 RoPE implementation are unrelated subsystems." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Wrong offset mappings and all-zero assistant masks are different tokenizer/chat-template bugs." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Multi-label classification returning empty results and mm_token_type_ids defaults are not the same issue." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and flash_attention_3 degenerate training are unrelated classification/modeling problems." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe loading and tokenizer_class metadata mismatch do not share a concrete code-path." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Dequantized save_pretrained issues and failing to load Phi-4 multimodal instruct are separate model lifecycle bugs." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading hang are not the same bug." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer behavior drift in v5 and Deepseek tokenizer incorrect results are different tokenizer regressions." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Qwen3-VL-Moe bug and position_ids buffer read error are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor parallel training bug and example-script multi-label classification empty outputs are different problems." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Saving dequantized models and gguf_file breaking from_pretrained are unrelated load/save bugs." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Missing Qwen2.5-VL export and missing HybridCache export are both import errors but not the same symbol or fix." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe loading and FP8 moe save_pretrained are distinct model-format issues." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3.5 save_pretrained regression and Qwen3.5 Moe from_pretrained error may be adjacent, but the titles point to different concrete failures and code-paths." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports from different packages; only the surface symptom matches." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 40, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42907", + "issue:43064", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43278", + "issue:43441", + "issue:43493", + "issue:43611", + "issue:43673", + "issue:43784", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44222", + "issue:44466", + "issue:44485", + "issue:44704", + "issue:44779", + "issue:44936", + "issue:44945", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45278", + "issue:45357", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45753", + "issue:46002" + ], + "soft_pairs": [ + "issue:43278|issue:44945", + "issue:43493|issue:45753", + "issue:42907|issue:44222", + "issue:43122|issue:44977", + "issue:43784|issue:45446", + "issue:43992|issue:44704", + "issue:43066|issue:44779", + "issue:38617|issue:45278", + "issue:42673|issue:45072", + "issue:43937|issue:44485", + "issue:22355|issue:29127", + "issue:43611|issue:46002", + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:42222|issue:43441", + "issue:43064|issue:43673", + "issue:43116|issue:43493", + "issue:44075|issue:44936", + "issue:45357|issue:45478", + "issue:44038|issue:45478", + "issue:43116|issue:43825", + "issue:45083|issue:45446", + "issue:43937|issue:45563", + "issue:44117|issue:45588", + "issue:33453|issue:39401", + "issue:39401|issue:44779", + "issue:43827|issue:45446", + "issue:44466|issue:46002", + "issue:43937|issue:44977", + "issue:42673|issue:43906" + ], + "prepared_review_unit_hash": "d897eed64f1c0384b4b0259ff5632702b739d5e3bdcd337426eb8bd6586cca82", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 35734, + "estimated_input_tokens": 8934, + "estimated_eval_tokens": 18124 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose mix of Transformers v5 regressions and model-specific bugs, not a set of true duplicates. I found no soft pair that shares the same concrete underlying failure mode closely enough to merge.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45278 is the broadest representative of the cluster\u2019s post-upgrade regression theme: it captures multiple import breakages after moving to 5.5.0, making it the best umbrella issue among otherwise narrow, unrelated reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most general, user-impacting issue in the set and best fits the cluster as a whole; the rest are mostly isolated model- or component-specific bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Different failures: dtype change during evaluate vs incorrect outputs under pipeline parallelism." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "Different model families and symptoms: SigLIP2 implementation discrepancy vs Qwen3.5 infinite-loop generation." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both are save-related, but they affect different model/quantization paths and do not look like the same bug." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer regression vs flash-attention generation failure; no shared concrete code-path." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Separate import-time errors in different packages/guards, with different missing symbols and causes." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Different from_pretrained/cached_file problems affecting different components." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer-related, but one is a decoder-type regression and the other is a Deepseek tokenization mismatch; not the same bug." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "45278 is a broad import-failure report, but 38617 is one specific missing symbol; too different in scope and root cause." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in multithreaded Qwen3ForCausalLM vs dtype mismatch in bfloat16 inference." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GenerationConfig validation error vs RoPE implementation discussion; unrelated failures." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Missing transformers.onnx module vs a LayoutLMv3 error-message clarity issue; unrelated." + }, + { + "left": "issue:43611", + "right": "issue:46002", + "accept": false, + "reason": "Loading models with base_model_prefix vs NaNs in classification heads; different code paths and symptoms." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 behavior warning/request vs missing image-patch method in an image processor; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version support regression vs a flex_attention import-version check bug." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "vitpose model breakage vs Ministral flash-attention failure; different models and failure modes." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption vs missing GenerationMixin cache during chunked prefill." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Empty multi-label classification outputs vs SigLIP2 implementation discrepancy; unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "SGD args ignored vs trainer.evaluate() failing after train(); not the same defect." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "Both touch Qwen3.5 MoE checkpoints, but one is save_pretrained key serialization and the other is a from_pretrained load error; distinct bugs." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen3 model variants and different failure modes; not a single concrete bug." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "run_classification empty outputs vs stale documentation/error messaging about pipeline translation support." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Qwen3_omni_moe feature-length helper bug vs flex_attention import guard issue; unrelated." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GenerationConfig invalid vs a stale warning about num_return_sequences; not the same underlying problem." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer mapping assumption bug vs flash_attention crashing on s_aux=None; unrelated." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Generic tokenizer-loading regression vs a specific Qwen3 offset_mapping bug; too broad to call duplicate." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenization regressions, but they affect different models and different symptoms." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing removed pipeline APIs vs a PyTorch-version import check bug; unrelated." + }, + { + "left": "issue:44466", + "right": "issue:46002", + "accept": false, + "reason": "Serialization of tied lm_head weights vs NaNs in classification heads; different issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 41, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42490", + "issue:42617", + "issue:42673", + "issue:42831", + "issue:43012", + "issue:43066", + "issue:43122", + "issue:43408", + "issue:43421", + "issue:43450", + "issue:43577", + "issue:43582", + "issue:43673", + "issue:43742", + "issue:43874", + "issue:43937", + "issue:43986", + "issue:44075", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44291", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44496", + "issue:44829", + "issue:44933", + "issue:45071", + "issue:45081", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45405", + "issue:45446", + "issue:45464", + "issue:45478", + "issue:45542", + "issue:45561", + "issue:45656" + ], + "soft_pairs": [ + "issue:43450|issue:43986", + "issue:44291|issue:45071", + "issue:45405|issue:45446", + "issue:45341|issue:45561", + "issue:44117|issue:45081", + "issue:38617|issue:41628", + "issue:39401|issue:43421", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:44484|issue:45310", + "issue:42371|issue:44261", + "issue:43408|issue:43742", + "issue:42673|issue:43582", + "issue:42617|issue:45341", + "issue:42222|issue:45542", + "issue:44933|issue:45278", + "issue:42490|issue:42673", + "issue:42175|issue:42222", + "issue:43937|issue:44496", + "issue:38617|issue:44220", + "issue:42371|issue:42831", + "issue:43066|issue:43122", + "issue:44483|issue:45464", + "issue:44075|issue:45656", + "issue:43673|issue:45341", + "issue:43012|issue:43577", + "issue:43874|issue:44261", + "issue:44484|issue:45478", + "issue:44410|issue:45478" + ], + "prepared_review_unit_hash": "6c4da4618f6640e8e4de47ed70e777ed40d417aa61b07524db031227d629cf31", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35629, + "estimated_input_tokens": 8908, + "estimated_eval_tokens": 18072 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is largely heterogeneous: several tokenizer/import/version-regression reports overlap superficially, but they do not appear to be the same underlying bug. No soft pair looks mergeable into a single issue or PR.", + "confidence": 0.86, + "canonical_issue_reason": "Issue 45278 is the closest umbrella candidate because it broadly covers import regressions after upgrading to 5.5.0, but the cluster is too mixed for a strong true canonical duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45278 is the most representative broad regression report in the set, but only as a loose umbrella; it is not a true duplicate of the other items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Both touch video-processing flows, but one is a shape bug and the other is a crash from missing torchvision; different failure modes and code paths." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "Both are v5 loading/type-related regressions, but one is an init_empty_weights argument issue and the other is a PreTrainedConfig type-checking break." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "Unrelated problems: a released-version dependency pin vs a PyTorch version check for flex_attention import." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Both mention testing utils, but one is a small bug and the other is an xdist race on captured_info.txt; not the same defect." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizer internals, but one is a mapping lookup returning None and the other is a Mistral regex patch crash." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and likely different API breakages." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Both are tokenizer behavior issues, but one is wrong offset mappings and the other is runtime special-token/post-processor sync." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Different Qwen-family issues: missing projections in qwen3next vs a from_pretrained error in Qwen3.5 MoE." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "One is a training degradation with flash_attention_3, the other is a save_pretrained checkpoint regression; different code paths." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "A max_shard_size question is unrelated to a Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API guidance and an rms_norm_eps precision bug are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "Different model-loading failures: a model-type mismatch warning vs a key error for a specific model." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "A VRAM leak in multithreaded Qwen3 inference and an Apple Silicon TypeError in caching_allocator_warmup are distinct issues." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel.py execution problem and a testing_utils bug are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "A broken VitPose model family and a backend detection issue with tensorboard-only installs do not share the same root cause." + }, + { + "left": "issue:44933", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-related, but 45278 is a broad upgrade regression while 44933 is a specific missing image_utils export." + }, + { + "left": "issue:42490", + "right": "issue:42673", + "accept": false, + "reason": "A trailing-slash local-path import warning and a VRAM leak in Qwen3 multithreaded use are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "Package/backend installation coverage and a broken VitPose model are different problems." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "One is a missing method on a vision processor fast class; the other is an unrecognized model/config issue." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "Both are generic framework bugs, but one is an import error and the other is an audio feature-extraction failure." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 configuration messaging and FineGrainedFP8 accuracy are not the same bug." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Both are tokenizer/version regressions, but one is a wrong decoder type and the other is changed tokenization output." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both involve chat/completions, but one is a general request rejection and the other is a streaming inference failure on a specific model." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "Both involve optimizers, but one says SGD args are ignored while the other says optimizer.step is called twice under deepspeed." + }, + { + "left": "issue:43673", + "right": "issue:45341", + "accept": false, + "reason": "A generation cache regression and a testing_utils bug are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Both mention dtype/precision, but one is a compile-time warning and the other is incorrect model dtype propagation on load." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "One is a missing image-patch-count method in a GLM vision processor, the other is an rms_norm_eps precision issue." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "A save_pretrained shard-size question is unrelated to a Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen-family failures: missing layer projections vs a from_pretrained error." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 42, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:38617", + "issue:41628", + "issue:42222", + "issue:42757", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43502", + "issue:43531", + "issue:43824", + "issue:43873", + "issue:43874", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44704", + "issue:44829", + "issue:44987", + "issue:45003", + "issue:45071", + "issue:45103", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45459", + "issue:45542", + "issue:45588" + ], + "soft_pairs": [ + "issue:44263|issue:44485", + "issue:43097|issue:44493", + "issue:42222|issue:45459", + "issue:41628|issue:45071", + "issue:43012|issue:43408", + "issue:43441|issue:44829", + "issue:45071|issue:45542", + "issue:43931|issue:44410", + "issue:43335|issue:45071", + "issue:43931|issue:44038", + "issue:45003|issue:45341", + "issue:43097|issue:43452", + "issue:43986|issue:45341", + "issue:43986|issue:44484", + "issue:44117|issue:44987", + "issue:43874|issue:44263", + "issue:43408|issue:44368", + "issue:43976|issue:45071", + "issue:43986|issue:45372", + "issue:43531|issue:45341", + "issue:38617|issue:42757", + "issue:44261|issue:44485", + "issue:43064|issue:44315", + "issue:44062|issue:44117", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "issue:43097|issue:45588", + "issue:44038|issue:44410", + "issue:44704|issue:45103", + "issue:43502|issue:43992", + "issue:43986|issue:44117", + "issue:43097|issue:43873", + "issue:43824|issue:43986", + "issue:43066|issue:43906", + "issue:43097|issue:43901" + ], + "prepared_review_unit_hash": "d1e3d1b36efb4acdc062cacd6d6adeec10755af6fbf94bb94ba4e6edcf70d78b", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37683, + "estimated_input_tokens": 9421, + "estimated_eval_tokens": 19098 + }, + "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 regressions: import errors, model-specific loading failures, config/warning regressions, and a few training/runtime bugs. None of the soft pairs look like the same underlying issue, so all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43097 is the broadest v5 compatibility regression in the set and the closest thing to a cluster hub; it has cross-references and reflects a general API break rather than a model-specific symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43097 is the best representative issue here because it captures generic Transformers v5 breakage with broader impact, while the others are narrower model- or dependency-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "Both are GLM-related, but one is a torch.split indexing bug and the other is a RoPE implementation issue; different code paths." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Both are v5 regressions, but one is a missing config flag warning and the other is an unexpected position_id key; not the same bug." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "Completely different symbols and dependencies: vitpose model breakage vs tokenizer protobuf error handling." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "Top-level import/type issues, but AutoImageProcessor import failure and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Both mention warnings, but a bfloat16 precision warning and a sam3_video/sam3_tracker type mismatch are distinct." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "FlashAttention is common, but one is a load-time failure and the other is a training-quality regression; not mergeable as one fix." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "No concrete overlap beyond being runtime regressions." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Same broad Qwen/VL family, but weight-shape mismatch and missing projection layers are different model bugs." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "Different scope: SwitchTransformers sparse-layer construction vs config type checking." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Both concern Qwen3-VL, but a load mismatch and a Qwen3-VL-Moe issue are different concrete failures." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated internals: sys.modules access vs a testing utility bug." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Both affect v5 loading, but gguf_file handling and a removed config option are distinct paths." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Video-model processor crash and testing_utils bug have no shared code path." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "Different features: torchvision-dependent processor loading vs shard-size documentation/behavior." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None and physical-intelligence/fast loading failure are not the same underlying bug." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Both GLM-related, but one is an image patch counter method missing and the other is torch.split return handling." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Different model families and warnings." + }, + { + "left": "issue:43976", + "right": "issue:45071", + "accept": false, + "reason": "Python-version compatibility vs config type checking; unrelated." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Processor-loading crash due to missing torchvision vs mistral_common import error; different dependencies and failures." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Sliding-window MoE behavior vs testing_utils bug; unrelated." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are ImportErrors from internal symbols, but they refer to different missing names/modules and likely different release breakages." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Both touch GLM-5-ish internals, but RMS epsilon config and RoPE implementation are separate numeric issues." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "Training/FSDP optimizer-state bug vs Liger-kernel application bug; different integration paths." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken argument duplication and tokenizer mapping None are separate tokenizer loader issues." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Both are Qwen config/model problems, but missing projections and a dropped vision-index config field are different concrete bugs." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Both are import failures, but layer_type_validation and HybridCache are unrelated symbols." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Both are Qwen3-VL/MoE related, but the reported failures are different model defects." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Processor kwargs forwarding and auto_docstring annotation handling are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "local_files_only networking bug vs missing embed_tokens weight loading are different issues." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Processor/vision dependency crash vs tokenizer mapping bug; unrelated." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Offloading/quantization behavior and tie_embeddings removal are different regressions." + }, + { + "left": "issue:43824", + "right": "issue:43986", + "accept": false, + "reason": "Qwen2.5-VL import error and video processor torchvision failure are different model/dependency paths." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "A tokenizer decoder-type regression and an isolated reproduction of another issue are not enough to treat as the same bug." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "Config warning removal and docs behavior mismatch 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": 1, + "component_count": 17, + "review_unit_index": 43, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42490", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43381", + "issue:43475", + "issue:43502", + "issue:43526", + "issue:43550", + "issue:43582", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43825", + "issue:43867", + "issue:43901", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44077", + "issue:44222", + "issue:44230", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:45216", + "issue:45290", + "issue:45381", + "issue:45478", + "issue:45479", + "issue:45753" + ], + "soft_pairs": [ + "issue:43825|issue:44655", + "issue:43992|issue:44484", + "issue:43208|issue:43550", + "issue:43012|issue:44368", + "issue:43352|issue:44380", + "issue:42886|issue:43381", + "issue:43012|issue:43550", + "issue:42907|issue:45753", + "issue:42907|issue:44655", + "issue:44380|issue:45479", + "issue:43352|issue:43976", + "issue:43064|issue:44380", + "issue:43208|issue:43526", + "issue:36683|issue:43582", + "issue:44483|issue:44514", + "issue:44222|issue:45478", + "issue:42490|issue:43012", + "issue:43012|issue:44683", + "issue:43618|issue:43761", + "issue:42757|issue:43824", + "issue:43618|issue:44380", + "issue:38617|issue:43502", + "issue:44038|issue:44230", + "issue:44483|issue:45290", + "issue:43756|issue:44485", + "issue:43299|issue:43867", + "issue:44483|issue:45381", + "issue:43901|issue:44655", + "issue:43299|issue:45753", + "issue:36683|issue:43475", + "issue:42994|issue:44655", + "issue:43352|issue:43937", + "issue:44077|issue:44380", + "issue:43867|issue:45216", + "issue:36010|issue:42757" + ], + "prepared_review_unit_hash": "9bca52a97ecbc9d979435660b9215d91f7ec0dbef26b27477f4676155c550424", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37361, + "estimated_input_tokens": 9341, + "estimated_eval_tokens": 18938 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a true duplicate set: the items span unrelated import errors, model-specific regressions, save/load issues, and API behavior bugs. None of the soft edges look like the same underlying change or bug.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue stands out; the cluster is too heterogeneous and the titles point to different code paths, models, and failure modes.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43825 is the most broadly framed, user-facing regression in the set, but it still does not represent the rest of the cluster well.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Different problems: v5 pipeline task messaging vs Pipeline.save_pretrained serialization." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Unrelated failures: missing embed_tokens weight vs max_shard_size behavior." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "Different models and bugs: xLSTM training blockers vs Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both mention warnings, but one is bfloat16 compilation and the other is a tie_word_embeddings config warning during Qwen fine-tuning." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Different code paths: Nemotron FlashAttention support check vs GPT2 attention-scaling being ignored." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading bug vs gradient checkpointing in eval mode are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "bfloat16 precision warning is unrelated to Bamba SDPA compilation failure." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Saving dequantized models is unrelated to a Qwen3.5 infinite-generation-loop bug." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Both involve saving, but one is dequantized model save logic and the other is Pipeline.save_pretrained." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention backend scaling bug is unrelated to the zero-loss classification issue." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Nemotron FlashAttention support and Python version compatibility are different issues." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "Distributed optimizer-state corruption is unrelated to GPT2 attention scaling." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training blockers and BeitImageProcessorFast label reduction are different bugs." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Gemma3Config missing vocab_size is unrelated to an Apple Silicon allocator TypeError." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "OpenAI chat/completions request handling is unrelated to apply_chat_template batching crash." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Moe/fp8 and Qwen3.5, but one is FP8 save_pretrained and the other is from_pretrained loading." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "Local path slash import warning is unrelated to bfloat16 compile warning." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "bfloat16 warning does not match compiled flex_attention failure on torch>=2.9." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both are CLIP regressions, but one drops attentions and the other drops hidden_states; not the same bug." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Different import errors from different packages/modules: huggingface_hub symbol vs a missing Transformers class export." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP output field assignment regression is unrelated to GPT2 attention scaling." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Missing configuration_utils import and unexpected online requests are different failure modes." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Both involve Qwen3-VL-Moe, but one is a v5 loading break and the other is fp8 inference support." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Chat completion API rejection is unrelated to assistant tool-call chat-template crashes." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Different RoPE-related models and fixes; these are not the same concrete bug." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL-Moe loading regression and sorted state_dict load error are not the same issue." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model save failure is different from saving Pipeline objects." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "FlashAttention support error is unrelated to GenerationConfig validation failure." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "patchtsmixer post_init validation is unrelated to GPT2 attention-scaling behavior." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "load_model state_dict sorting error and incorrect saved checkpoint output are different directions of the serialization path." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Two different import errors from different symbols/modules; no shared 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": 1, + "component_count": 17, + "review_unit_index": 44, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42490", + "issue:42890", + "issue:42898", + "issue:43010", + "issue:43064", + "issue:43066", + "issue:43352", + "issue:43525", + "issue:43575", + "issue:43611", + "issue:43618", + "issue:43867", + "issue:43931", + "issue:43976", + "issue:43992", + "issue:44075", + "issue:44077", + "issue:44188", + "issue:44242", + "issue:44246", + "issue:44263", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44484", + "issue:44492", + "issue:44655", + "issue:44855", + "issue:44857", + "issue:44938", + "issue:44977", + "issue:45071", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45561", + "issue:45593", + "issue:45850" + ], + "soft_pairs": [ + "issue:42898|issue:43066", + "issue:36683|issue:44077", + "issue:43611|issue:44655", + "issue:43976|issue:44938", + "issue:36683|issue:43525", + "issue:43352|issue:45593", + "issue:43618|issue:45216", + "issue:44263|issue:45440", + "issue:36683|issue:44242", + "issue:44188|issue:44380", + "issue:43064|issue:44492", + "issue:43352|issue:43931", + "issue:43992|issue:45310", + "issue:43010|issue:45278", + "issue:43867|issue:45375", + "issue:41669|issue:44246", + "issue:44355|issue:44855", + "issue:36683|issue:43064", + "issue:42890|issue:45561", + "issue:44938|issue:45071", + "issue:43867|issue:45357", + "issue:43010|issue:45850", + "issue:43992|issue:45478", + "issue:43010|issue:43976", + "issue:44938|issue:45381", + "issue:43618|issue:44077", + "issue:42490|issue:44075", + "issue:36296|issue:43575", + "issue:44360|issue:45440", + "issue:28282|issue:33453", + "issue:43867|issue:44484", + "issue:43618|issue:44857", + "issue:43618|issue:44977" + ], + "prepared_review_unit_hash": "3aea0afb79d4415ca791cd63fdd2b996a98669e303975976408185eba7cc3431", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37070, + "estimated_input_tokens": 9268, + "estimated_eval_tokens": 18792 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of Transformers v5 regression reports: import/load failures, model-specific config/key mismatches, tokenizer behavior changes, and a few performance/parallelism issues. The only plausible duplicate edge is the import-time slowdown pair.", + "confidence": 0.58, + "canonical_issue_reason": "issue:45278 is the broadest representative of the shared v5 breakage/import-regression theme across the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most representative issue because it captures the broad version-upgrade regression pattern rather than a single model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42898", + "right": "issue:43066", + "accept": false, + "reason": "Both are tokenizer-related v5 changes, but one is about clean-up spacing behavior and the other about decoder type; different bugs." + }, + { + "left": "issue:36683", + "right": "issue:44077", + "accept": false, + "reason": "Missing Gemma3 config attrs and patchtsmixer post_init gating are unrelated model-specific issues." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "Base-model-prefix loading breakage and Pipeline save_pretrained failure affect different code paths." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Both concern Python-version compatibility, but they report different failures and likely different causes." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Gemma3 missing vocab_size and Llama4 missing pad_token_id are separate config omissions." + }, + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "Flash Attention support error for Nemotron is unrelated to D-FINE auxiliary-loss handling." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIPOutput attentions assignment and Qwen3.5 save_pretrained checkpoint corruption are different bugs." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "GlmMoeDsaIndexer torch.split behavior and DeepseekV3MoE divergence are different model implementation issues." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Missing Gemma3Config vocab_size and missing load-balancing loss with output_router_logits=False are unrelated." + }, + { + "left": "issue:44188", + "right": "issue:44380", + "accept": false, + "reason": "Both mention attention behavior, but one is a compile-time branching issue and the other is backend scaling config handling." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to a cache-strategy typo." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "Nemotron Flash Attention support and Qwen3-VL weight-shape mismatch are unrelated model-specific failures." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Both involve from_pretrained errors, but for different models and different missing-state behavior." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Cache update no_grad decoration is unrelated to broad import-error regressions." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "A sorted-state_dict load error and a missing Qwen3_5MoeVisionConfig field are different issues." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "Both point to the same import-time slowdown problem; one explicitly identifies wildcard imports in models as the cause." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Running compiled Python files and TorchScript parse/IndentationError on Python 3.13 are different failure modes." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Config attribute absence and FSDP2/PEFT optimizer-state mismatch are unrelated." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Seed-related flaky tests and xdist race on captured_info.txt are different testing issues." + }, + { + "left": "issue:44938", + "right": "issue:45071", + "accept": false, + "reason": "Python 3.14 import failure and PretrainedConfig type-checking regression are different problems." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "These are both save/load regressions, but one is a generic state_dict ordering issue and the other is Qwen3.5 visual-key corruption." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "No-grad cache updates and a generic complaint that v5 breaks too many models are not the same bug." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "Both are from_pretrained errors, but they target different Qwen variants and different symptoms." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache update semantics and Python-version compatibility are unrelated." + }, + { + "left": "issue:44938", + "right": "issue:45381", + "accept": false, + "reason": "Python 3.14 load failure and Qwen2.5-VL video vision_position_ids bug are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44077", + "accept": false, + "reason": "CLIPOutput attentions regression and patchtsmixer post_init policy are different issues." + }, + { + "left": "issue:42490", + "right": "issue:44075", + "accept": false, + "reason": "Local-path import warning and SGD optimizer args not being used are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Tensor-parallel training bug and Qwen2-57B-A14B-Instruct OOM are different scaling problems." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer ReLU discussion and DeepseekV3MoE divergence are unrelated implementation issues." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "AutoModel missing PyTorch and tokenizer loading regression are different loading failures." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Generic model-loading error and max_shard_size behavior/question are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "CLIP attentions regression and LwDetrImageLoss AMP crash are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "CLIP attentions assignment and Qwen3.5 flash-attention generation failure are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the cluster does look like a mix of v5 regression reports spanning import/load failures, tokenizer changes, config/key mismatches, and a few performance/parallelism issues. The canonical issue choice is reasonable as a broad representative, and the one accepted soft-edge pair (41669/44246) is a plausible duplicate on import-time slowdown. The rejected pairs are mostly conservative and do not overclaim sameness based on weak title similarity alone." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 45, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43065", + "issue:43232", + "issue:43299", + "issue:43502", + "issue:43576", + "issue:43673", + "issue:43723", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:44062", + "issue:44112", + "issue:44222", + "issue:44230", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44387", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44655", + "issue:44749", + "issue:44908", + "issue:44938", + "issue:44961", + "issue:44964", + "issue:45071", + "issue:45125", + "issue:45341", + "issue:45375", + "issue:45468", + "issue:45478", + "issue:45600" + ], + "soft_pairs": [ + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:43723|issue:44556", + "issue:44222|issue:45125", + "issue:44387|issue:44556", + "issue:42890|issue:45341", + "issue:42548|issue:44351", + "issue:43010|issue:43065", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:45125|issue:45478", + "issue:30990|issue:31795", + "issue:43010|issue:43232", + "issue:45125|issue:45375", + "issue:30333|issue:33453", + "issue:43299|issue:44556", + "issue:43502|issue:44222", + "issue:42831|issue:43874", + "issue:44315|issue:44360", + "issue:43502|issue:44961", + "issue:44355|issue:45071", + "issue:30333|issue:36296", + "issue:44355|issue:44655", + "issue:43827|issue:44961", + "issue:44222|issue:44230", + "issue:33453|issue:34689", + "issue:42757|issue:43576", + "issue:33453|issue:36296", + "issue:43576|issue:45071", + "issue:43576|issue:43824", + "issue:31795|issue:38617", + "issue:41628|issue:42548", + "issue:44961|issue:45468", + "issue:38617|issue:43576", + "issue:43576|issue:44938", + "issue:43673|issue:44492", + "issue:44908|issue:44961", + "issue:44485|issue:44961" + ], + "prepared_review_unit_hash": "dd0001691f318a3e65fce21d50a06beffabcb49b697492f2d1ca72f8bad9a163", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 40, + "serialized_chars": 39022, + "estimated_input_tokens": 9756, + "estimated_eval_tokens": 19768 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is noisy and spans many unrelated Transformers issues: import errors, model-loading regressions, test flakiness, docs, FP8/quantization, and other model-specific bugs. None of the proposed soft pairs look like the same underlying defect.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue stands out: the items are not duplicates of one another and cover several distinct bug classes.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a good global canonical representative because the cluster is heterogeneous rather than one concrete bug family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "SamHQ integration-test flakiness is unrelated to a Phi-4 multimodal model-loading failure." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Different failures: missing set_seed in SamHQ tests vs a GraniteSpeech CI device-override issue." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "SamHQ test nondeterminism is not the same as stale auto_mappings references to removed Sam3LiteText configs." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "A local_files_only network leak and an AddedToken keyword collision are unrelated code paths." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Both mention loading, but one is AutoTokenizer loading in v5 and the other is checkpoint reload after a version upgrade; not the same bug." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained for MoE and a missing tensor-parallel plan are distinct issues." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 quantization OOM and checkpoint reload incompatibility are different regressions." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "A SamHQ flaky test is not the same as a generic testing_utils bug." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Missing PreTrainedModel import and missing HybridCache import are separate symbol-export problems." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "Cache update no_grad behavior and a dummy Conv2d in Sam3PixelDecoder are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Local-files-only network requests do not match a GLM-5 RoPE implementation bug." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python file load errors and a training/filtering slowdown after upgrade are different symptoms." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "A missing _tp_plan for tensor parallelism is not the same as a Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Sentence Transformers getting stuck loading is unrelated to documentation confusion in model.forward." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Decorating cache update methods with no_grad is a different change than fixing generation kwargs after sync_gpus." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Tensor-parallel planning and a missing config field silently dropped by @strict are different bugs." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLFlow failure reporting and a tokenizer-loading regression are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Qwen3VL MoE loading in v5.0.0.dev0 and reload failure after upgrading to v5.2/v5.3 are not the same concrete issue." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "A local_files_only API leak is unrelated to FP8 save_pretrained for MoE models." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "An FP8 accuracy issue and a missing image-processor method are different defects." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel not applied via model_init has nothing to do with the DSA indexer ReLU discussion." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "A real loading/network regression and an unrelated placeholder issue titled 'racoon' are not duplicates." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled Python file errors and v5.4.0 PretrainedConfig type-checking breakage are different problems." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLFlow job status reporting and tensor-parallel training bugs are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled-file loading errors and inability to save Pipeline objects are different code paths." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still referencing pipeline() and an unrelated 'racoon' issue are not the same bug." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both mention FP8/MoE, but one is about saving pretrained weights and the other about inference support." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 90B Vision model loading breakage are different concrete failures." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "An import error from huggingface_hub is not the same as the transformers env command breaking in v5." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Broken transformers env command and PretrainedConfig type-checking regression are different issues." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "The env command bug and AutoTokenizer/AutoImageProcessor import failures are not the same underlying defect." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion in model.forward is unrelated to a missing layer_type_validation import." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "AutoImageProcessor import failure and PreTrainedModel import failure are separate symbol export regressions." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "The placeholder 'racoon' issue is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "Missing layer_type_validation import and the v5 env-command failure are different bugs." + }, + { + "left": "issue:43576", + "right": "issue:44938", + "accept": false, + "reason": "Broken env command and Python 3.14 load failure are distinct issues." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked-prefill GenerationMixin cache missing and a cache-strategy typo are not the same defect." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs handling is unrelated to the placeholder issue titled 'racoon'." + }, + { + "left": "issue:44485", + "right": "issue:44961", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to the placeholder issue titled 'racoon'." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 46, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:36296", + "issue:41628", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44246", + "issue:44261", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44393", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44704", + "issue:44861", + "issue:44908", + "issue:44945", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45341", + "issue:45362", + "issue:45478", + "issue:45542", + "issue:45753", + "issue:45850" + ], + "soft_pairs": [ + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "issue:36296|issue:43526", + "issue:45362|issue:45850", + "issue:44261|issue:44360", + "issue:44623|issue:45230", + "issue:44273|issue:45542", + "issue:44273|issue:45003", + "issue:44393|issue:45753", + "issue:44038|issue:45125", + "issue:43576|issue:44556", + "issue:44393|issue:45071", + "issue:43525|issue:45850", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:44492|issue:45850", + "issue:43572|issue:45850", + "issue:42371|issue:44492", + "issue:44704|issue:44908", + "issue:42890|issue:44908", + "issue:45278|issue:45850", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:43976|issue:44393", + "issue:43352|issue:44393", + "issue:44297|issue:45230", + "issue:43576|issue:44908", + "issue:44295|issue:45230", + "issue:44908|issue:45071", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:44492|issue:44945", + "issue:43874|issue:45850", + "issue:44393|issue:45478", + "issue:44077|issue:44861", + "issue:43827|issue:44908" + ], + "prepared_review_unit_hash": "7588574c097c40b5ccdc321659af7560da00851486951b0997ed2d0832dc4d2e", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 36, + "serialized_chars": 37285, + "estimated_input_tokens": 9322, + "estimated_eval_tokens": 18900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: a few v5-regression complaints, several model-specific bugs, and multiple unrelated issues. I do not see any pair with enough evidence to treat as the same underlying bug/change, and there are no PRs to consider.", + "confidence": 0.88, + "canonical_issue_reason": "issue:45850 is the best umbrella-style issue in the set because it broadly summarizes v5 breakage, but it is too vague to serve as a precise duplicate target for the specific bugs here.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the best overall representative because it is the only broad, current meta-report; however, the cluster is not a single cohesive defect.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor parallel training bug vs docs mentioning return_all_scores; unrelated topics." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "AutoImageProcessor import error vs compiled Python file errors; different failure modes." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor parallel training vs BeitImageProcessorFast reduce_labels bug; no overlap in code path." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Specific Qwen3.5-35B chat crash vs a broad meta complaint about many models; not the same bug." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "Layernorm precision/config issue vs DSA indexer ReLU discussion; unrelated." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Specific save_pretrained missing-files bug vs a generic bug report title; no concrete match." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading problem vs missing TensorFlow backend when only tensorboard is installed; different issues." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Possible loose relation via lazy loading, but titles point to different bugs and code paths." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Different Qwen3-VL/Qwen3.5 image issues with different symptoms; not clearly the same defect." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Qwen3-VL-Moe bug vs missing _tp_plan for Qwen3_5Moe tensor parallelism; distinct failures." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Broken transformers env command vs checkpoint reload after upgrade; both v5-related but separate problems." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Vision bounding-box output issue vs PretrainedConfig type-checking breakage; unrelated." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Llama4Config pad_token_id attribute error is model-specific, not the same as the broad v5 regression meta issue." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import * performance regression vs missing GenerationMixin cache in chunked_prefill; different subsystems and symptoms." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both involve v5 compatibility, but one is checkpoint reload and the other is remote-code/meta-init incompatibility; not one bug." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "Typo in cache strategy wording vs broad model breakage complaint; no shared defect." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression is specific and not the same as a general v5 breakage report." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API settings guidance vs cache strategy typo; unrelated." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor cached_file kwargs forwarding vs inverse_sqrt scheduler kwargs; different APIs." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Missing set_seed in SamHQ tests vs scheduler kwargs handling; unrelated." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Many import errors after upgrade is broader but still a different report from 'too many models break'; not the same concrete issue." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Import performance sometimes slow vs lazy loading not working properly; related theme, but not the same underlying bug." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "sam3_video/sam3_tracker type warning vs Liger Kernel not applied with model_init; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version compatibility vs Qwen3-VL bounding-box output bug; unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support error vs vision model output hallucination; different code paths." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch vs generic bug report; no evidence they are the same issue." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Environment command regression vs scheduler kwargs bug; not the same defect." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "position_ids buffer access error vs generic bug report; no match." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs ignored vs config type-checking breakage; unrelated." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import * performance problem vs HybridCache import error; different issues." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Import performance regression vs a testing_utils bug; unrelated." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache strategy typo vs pipeline parallelism output correctness; unrelated." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "GLM46V missing method bug is model-specific and not the same as the broad v5 breakage complaint." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3-VL bounding-box output issue vs Qwen3.5 Moe from_pretrained error; different models and symptoms." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "PatchTSMixer post_init validation issue vs tied weight key attribute crash; unrelated." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() vs scheduler kwargs handling; documentation and runtime bug are different." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 47, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "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:43618", + "issue:43704", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44315", + "issue:44360", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44655", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45092", + "issue:45230", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45850" + ], + "soft_pairs": [ + "issue:31795|issue:33453", + "issue:41669|issue:44908", + "issue:44315|issue:44829", + "issue:43576|issue:44273", + "issue:44655|issue:44861", + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:41669|issue:43704", + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "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:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44492|issue:44998", + "issue:44861|issue:45290", + "issue:44998|issue:45850", + "issue:43618|issue:44998", + "issue:44998|issue:45341", + "issue:43525|issue:44861", + "issue:43572|issue:44861", + "issue:31515|issue:38617", + "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": "3d8ea24ce17851162fea502cf03773ee5ee3996a059a72bcf0186c62cca178c9", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 42, + "item_count": 42, + "soft_pair_count": 40, + "serialized_chars": 35533, + "estimated_input_tokens": 8884, + "estimated_eval_tokens": 18024 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is still mostly heterogeneous. The tokenizer pair (42913/43066) is clearly related and likely stems from the same v5 tokenizer transition, but with only title-level evidence it should be treated as possibly related rather than a definite duplicate. The rest of the soft edges remain conservative rejections across different code paths or features.", + "confidence": 0.78, + "canonical_issue_reason": "issue:42913 is the broadest tokenizer-v5 regression report in the set; issue:43066 looks closely related, but the available evidence is not strong enough to treat them as the same bug with high confidence.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42913 is the best overall issue candidate because it captures the broader user-visible tokenizer behavior change, making it the most useful umbrella if the pair later proves to be the same underlying regression.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Different problems: documentation confusion vs tokenizer loading regression." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Unrelated: import-star cleanup/perf issue vs scheduler kwarg handling." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Both are training-related, but they describe different failure modes and code paths." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Different features: env command breakage vs lazy loading behavior." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving pipeline objects is unrelated to tied-weight key crash handling." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA indexer activation issue vs Gemma-4 audio positional encoding bug." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report vs a specific Qwen3.5 MoE from_pretrained regression." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading and inverse_sqrt scheduler kwargs are different subsystems." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp bug vs GLM-5 RoPE implementation issue." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "No shared code path: processor timestamp math vs scheduler configuration." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star refactor/perf discussion is unrelated to VRAM leakage in multi-threaded loading." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion is not the same as a model-loading regression for a specific checkpoint." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Different surfaces: model.forward docs vs flash-attention import error." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Both touch model creation/loading, but the concrete incompatibilities differ." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "Different model architectures and different implementation bugs." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in threaded inference is unrelated to RoPE math." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 settings API change is unrelated to the dataloader-thread VRAM leak." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "Local-files-only network access bug is unrelated to processor timestamp calculation." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Processor timestamp bug and save_pretrained missing files are different code paths." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Processor timestamp logic vs multi-thread VRAM leak are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "Different low-level math/indexing issues in different models." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to Gemma-4 positional encoding." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Precision/config epsilon issue is not the same as Gemma-4 audio encoding bug." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Highly related tokenizer-v5 reports, but title-level evidence is not enough to call them a definite duplicate or the same regression." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs bug is unrelated to an unemployment placeholder issue." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "Typo in cache strategy naming is unrelated to the placeholder issue." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight-key crash and chat-template tool-call crash are different failure points." + }, + { + "left": "issue:44998", + "right": "issue:45850", + "accept": false, + "reason": "Placeholder/unemployment issue is unrelated to a broad v5 breakage complaint." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to the placeholder issue." + }, + { + "left": "issue:44998", + "right": "issue:45341", + "accept": false, + "reason": "Unemployment placeholder is unrelated to a testing_utils bug." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config is unrelated to tied-weight key handling." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression is unrelated to tied-weight key extraction." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Checkpoint loading slowness and missing import errors are different issues." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 inference support request is unrelated to processor save_pretrained file omissions." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow reporting on failed training jobs is unrelated to checkpoint loading speed." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint loading slowdown vs tensor-parallel training bug are different problems." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Loading performance issue and model.forward documentation confusion do not share the same code path." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "FP8 support request is unrelated to Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Checkpoint load slowness and tokenizer loading regression are different behaviors." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching audio support and FP8 inference support are separate feature gaps." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The analysis is mostly grounded, but it overstates the tokenizer pair: from the packet we can see strong topical similarity between issue:42913 and issue:43066, yet not enough to call them a clear duplicate or the same regression with confidence. The summary should hedge more (e.g., 'likely related' or 'possibly duplicate') unless there is body-level evidence. The rest of the soft-edge rejections are conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "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": "482c132974ebc86002c363525641bbdfcd419c87d0a5b54f721f1dcb3804d248", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2477, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2477, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The three issues do not look like duplicates of one another: one is about Tapas tokenization behavior, one about a private-model download/login error message, and one about a generic model-loading failure for bert-base-uncased.", + "confidence": 0.95, + "canonical_issue_reason": "There is no strong canonical duplicate here; the reports describe different failure modes. If forced to anchor the cluster, issue 16618 is the broadest model-loading report, but it still does not match the other two.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 16618 is the best anchor only in the sense that it is the most general and discussed model-loading complaint. It is still not a true duplicate of the Tapas tokenization or private-model/login issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Tapas tokenization mismatch is a different underlying problem from a bert-base-uncased model-loading failure." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Private-model download/login error message is unrelated to the generic 'can't load model' report." + } + ] + }, + "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": 17, + "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": "dde3b2433053bdb37098a6c94b94df50ac6c09ecf824fac3610b1bb3c8eaad46", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "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 unrelated community contribution feature requests: one for Flash Attention 2 support across more architectures, and one for GGUF support across more architectures. They are not the same underlying bug/change, so this cluster should not be merged as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 26350 is the better representative of the pair only in a superficial sense because it has substantially more discussion activity, but it is not a canonical duplicate of issue 33260.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different feature areas and code paths: Flash Attention 2 support versus GGUF support. They share only a broad theme of adding architecture support, not the same underlying 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": 17, + "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-27088-5", + "nodes": [ + "issue:27088", + "issue:28936", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:27088|issue:28936", + "issue:28936|issue:43834", + "issue:28936|issue:44365", + "issue:28936|issue:44370", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "450c0ab5018b102e02fe9c93ea3087291043bb36c8a87aa00417fd6462a99c8c", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 10, + "serialized_chars": 6442, + "estimated_input_tokens": 1611, + "estimated_eval_tokens": 3478 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 10, + "serialized_chars": 6442, + "estimated_input_tokens": 1611, + "estimated_eval_tokens": 3478 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster mixes two concrete locale requests (Turkish, Spanish) with three near-identical generic template issues. The generic template issues are the best representative of the cluster, but none of the pairs are strong enough to merge as duplicates.", + "confidence": 0.92, + "canonical_issue_reason": "issue:44365 is the cleanest representative of the near-identical generic template-style issues; the Turkish and Spanish issues are distinct locale-specific requests.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44365 best captures the cluster\u2019s shared template wording and is closest to the other generic entries.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Turkish docs translation and a generic placeholder translation issue are not the same concrete request." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Turkish locale request versus a generic template issue; different underlying task." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Concrete Turkish translation request does not match the generic placeholder issue." + }, + { + "left": "issue:27088", + "right": "issue:28936", + "accept": false, + "reason": "Different target languages (Turkish vs Spanish) make these distinct issues." + }, + { + "left": "issue:28936", + "right": "issue:43834", + "accept": false, + "reason": "Spanish translation request is not the same as the generic template issue." + }, + { + "left": "issue:28936", + "right": "issue:44365", + "accept": false, + "reason": "Spanish locale request versus a generic placeholder issue; not the same underlying bug/change." + }, + { + "left": "issue:28936", + "right": "issue:44370", + "accept": false, + "reason": "Different concrete locale requests; only broad translation theme is shared." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "These are near-identical template issues, but the evidence is insufficient to say they are the same concrete issue." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Highly similar generic wording, but no explicit evidence of one underlying issue rather than repeated template entries." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "Nearly identical placeholder text, but not enough proof they refer to the same concrete task." + } + ] + }, + "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": 17, + "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:36879|issue:37015", + "issue:37015|issue:42503", + "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:43671|issue:43909", + "issue:43837|issue:43909", + "issue:43837|issue:45322", + "issue:43837|issue:44121", + "issue:43909|issue:44205", + "issue:44121|issue:45322", + "issue:43837|issue:45027", + "issue:37015|issue:45027", + "issue:43837|issue:45177" + ], + "prepared_review_unit_hash": "6a52ed0d3a7b09a51fdcaa56a1c4a79e48b8c0ffd821a2496aa43c1baa34260b", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20706, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20706, + "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 a collection of broadly similar model-addition requests, but the underlying models, modalities, and code paths are different. I do not see true duplicates or a single canonical issue/PR for merge triage.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "EuroBert config support vs DEIMv2 addition: different model families and likely different implementation paths." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert model config request vs Qwen3-TTS speech support; unrelated modalities and code changes." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert config vs RF-DETR object detection model; different architecture and files to touch." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are distinct vision models; same broad subsystem, but not the same underlying change." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR detector vs LFM2.5 Audio model; different modality and implementation scope." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR addition vs a sparse transformer request; unrelated model families and code paths." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR detection model vs Qwen3-ASR speech recognition; different modality and concrete change." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR detection model vs Qwen3-TTS support; not the same bug/change." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT text model request vs Qwen3-ASR speech request; different model targets." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT addition vs sparse transformer support; different architecture and likely different files." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT vs LFM2.5 Audio; text model request and audio model request are not duplicates." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are unrelated model additions across different domains." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are different model requests; only broad theme of adding a model." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture request vs Qwen3-ASR support; different model families and tasks." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 architecture vs weight-sparse transformer request; not the same concrete change." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 architecture request vs ModernVBERT models; distinct model integrations." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 architecture vs Voxtral TTS support; unrelated model/task." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 vision model request vs Qwen3-TTS speech support; different modality and code path." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT models vs Qwen3-ASR support; different model family and task." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT models vs Qwen3-TTS support; not the same underlying change." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT model addition vs broad BERT-like RoPE discussion; related theme but not a duplicate." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like RoPE architecture discussion vs Voxtral TTS support; unrelated request scope." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS vs Qwen3-ASR are related by family name but target different speech tasks and fixes." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Both are speech-related, but Qwen3-TTS and Voxtral-4B-TTS-2603 are different model integrations." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS support vs DeepSeek-OCR2 addition; different modalities and code paths." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS support vs sparse transformer request; different model class and implementation." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio are both audio-related but still distinct model requests." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio are separate speech-model requests, not the same change." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR support vs EUPE model request; different model families and functionality." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR speech support vs sparse transformer request; unrelated code paths." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio vs SAM3-LiteText; audio model request versus vision/text model request." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Sparse transformer model request vs EUPE encoder request; distinct architectures and fixes." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR is speech recognition, while Voxtral-4B-TTS-2603 is text-to-speech; opposite tasks." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT text model request vs Voxtral TTS support; unrelated model additions." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR speech support vs DeepSeek-OCR2; different model domains and code 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": 17, + "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": "abd24aa4ec8712eb8c481d9e4576fa44d8d857b0de0b0dfd84a082c73bbba98c", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6288, + "estimated_input_tokens": 1572, + "estimated_eval_tokens": 3400 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6288, + "estimated_input_tokens": 1572, + "estimated_eval_tokens": 3400 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are a loose similarity cluster, not a duplicate set: they cover unrelated bugs across model configs, loss plumbing, quantization typos, and tokenizer warnings. No pair looks like the same underlying fix.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Both mention normalization, but one asks about Llama4TextL2Norm semantics while the other is a ModernBERTConfig type-hint issue; different models and different defect types." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Unrelated bugs: Mask2Former ignore_value is unused, versus kwargs not being forwarded to a loss function." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Different subsystems and symptoms: Mask2Former loss parameter handling versus tokenizer regex warning behavior." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Mask2Former ignore_value handling is unrelated to a typo in a quantization attribute name." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "One is a model-loss parameter bug, the other is a config type-hint mistake in a different model." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss-kwargs forwarding bug and ModernBERTConfig type annotation bug are distinct code paths and fixes." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "A config type hint issue is not the same underlying problem as tokenizer regex warnings after a version change." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "ModernBERTConfig norm_eps typing and the quantization_operation typo are unrelated changes." + } + ] + }, + "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": 17, + "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": "651d192913ec6eec67697e1ade1dd96774269597b3950612700611f589bf9bba", + "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": "The two issues are unrelated: one asks for block decoding support, the other for DeepSeek v3.2 support. They should not be deduplicated.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue; the requests target different features/problem domains.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither is a duplicate of the other. If one must represent the cluster, 'DeepSeek v3.2 support' is the clearer standalone feature request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different underlying requests: block decoding implementation vs DeepSeek v3.2 model support. They share no concrete 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": 17, + "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": "6c435e1d99eb3655afb5f87c4e82b59593e2891a8719dca43f33696443f93722", + "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": "Two closed issues touch Trainer customization, but they describe different problems: one about `remove_unused_column` behavior, the other about FLOPs estimation for custom trainers. They are related in theme, not the same underlying bug.", + "confidence": 0.89, + "canonical_issue_reason": "Issue #43598 is the stronger canonical issue because it states a concrete Trainer behavior (`remove_unused_column`) and a specific customization limitation, making the scope clearer.", + "canonical_pr_reason": null, + "best_issue_reason": "#43598 is the best representative issue: it is narrowly actionable and describes an explicit Trainer setting that likely needs design/behavior changes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "The issues concern different code paths and outcomes: one is about unused-column removal in Trainer data handling, the other about FLOPs accounting for custom trainers. Shared customization context is not enough to treat them as duplicates." + } + ] + }, + "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": 17, + "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": "f7e521b2970c2a7842af7f4234efce91d1aa4351c4b6a173b1ded8855040ba6e", + "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 different feature requests for different Qwen model families and different AutoModel heads, so they should not be clustered as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43684 is the broader request and is specifically about registering Qwen3-Omni with AutoModel and AutoModelForConditionalGeneration, which is the clearest standalone issue here.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43684 is the best representative because it names the concrete registration gap and is broader than the more specialized sequence-classification request in 44405.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different model variants and different tasks: Qwen3-Omni registration for base/generation auto classes versus Qwen3.5 sequence-classification support. They do not appear to be the same underlying 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": 10, + "component_count": 17, + "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": "e4931f27018694fbc8f63c50aa15a21db45e1d1820b2e87bbe638a99013d98ac", + "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": "All four issues are too under-specified to confidently deduplicate. Three share the same vague title, but there is no body/context to confirm they describe the same underlying problem; the lone different title looks unrelated.", + "confidence": 0.32, + "canonical_issue_reason": "issue:43845 is the best placeholder canonical issue because it is the earliest of the repeated 'huggingface' titles, but the cluster lacks enough detail to establish a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43845 is the strongest issue candidate only by virtue of being the earliest repeated-title report; still, the report content is too thin to be a reliable canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Titles do not match, and there is no body/detail tying 'Fett' to the 'huggingface' reports." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "No substantive evidence of the same underlying bug; titles are unrelated." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "No content links this issue to the 'huggingface' reports." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": false, + "reason": "Identical vague titles are not enough to confirm the same bug without body/context." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": false, + "reason": "Same broad title, but no description or targets to verify a shared underlying issue." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": false, + "reason": "Same repeated title, but insufficient evidence to treat them as definite duplicates." + } + ] + }, + "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": 17, + "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": "e7553489ffd9fd8dd1946c6ae387cdb2f37296faf2f0adff2aa79a41ca7d5d28", + "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": "These are low-signal, likely unrelated spam/placeholder issues. Two pairs share the exact same placeholder title, but there is no evidence of a shared underlying bug or concrete change, so no soft merges are justified.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44371 is the earliest and simplest representative of the spam-like cluster, but only as a bookkeeping anchor rather than because it clearly matches a real underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44371 is the best single issue to keep as the cluster representative because it is earliest and generic, but the cluster itself does not appear to describe a real deduplicable issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Same placeholder title, but the content is too empty to establish the same underlying issue or bug." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Same placeholder title, but no concrete evidence links them to the same problem." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "These titles are not meaningfully the same issue; one is spam-like and the other is a generic documentation suggestion." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "No shared bug/change is visible; the titles are unrelated." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "Generic documentation suggestion versus spam placeholder; no same underlying issue is evident." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Generic documentation suggestion versus spam placeholder; not the same concrete problem." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Identical placeholder titles alone are not enough to confirm the same underlying bug or change." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "No concrete overlap beyond low-signal similarity; the titles do not indicate the same issue." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "No concrete overlap beyond low-signal similarity; the titles do not indicate 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": 12, + "component_count": 17, + "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": "18ff4fd5a3b447a07bf1f906b8f1152897c2896f2b36757fb50f2a162fa6d0cd", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1645, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1645, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two closed issues have identical titles and fairly similar lengths, but the packet only provides soft-similarity evidence. With no explicit links, shared targets, or body-level confirmation, this should be treated as a tentative match rather than a confirmed duplicate. The soft edge is rejected.", + "confidence": 0.71, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45145 is the best provisional issue candidate because it is earlier and already has an inbound reference, but the evidence is not strong enough to confirm a duplicate/canonical merge.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "Identical titles and soft similarity alone are not enough to confirm the same underlying issue. The packet does not show near-identical bodies, explicit links, or shared targets, and deterministic_accept is false." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports only a soft-similarity match and identical titles; it does not show the bodies are near-identical or that these are definitely duplicates. The soft-edge verdict is too strong: deterministic_accept is false in the packet, so a conservative verdict would be uncertain or tentative rather than accept." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 17, + "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": 17, + "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": "d777f1c0f728e4c2f0d9379e5a5d306a24a02001acda5f42275aa70ac42f104c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues both involve 4-bit inference behavior in the Gemma/BitsAndBytes stack, but they describe different failures: one is a torch.finfo() TypeError triggered by uint8 weights in audio modules, and the other is an AssertionError caused by llm_int8_skip_modules clearing the default lm_head exclusion. They are related by broad quantization context, not the same underlying bug.", + "confidence": 0.95, + "canonical_issue_reason": "Issue #45674 is the better canonical issue for the cluster only if one wants the broadest 4-bit BitsAndBytes inference regression bucket, but the reports are not duplicates and should stay separate. #45672 is more specific to Gemma4 audio-module dtype handling; #45674 is a distinct configuration/skip-modules bug.", + "canonical_pr_reason": null, + "best_issue_reason": "#45674 is the stronger standalone issue for a generic 4-bit inference regression because it includes a clear configuration trigger and an AssertionError tied to BitsAndBytesConfig behavior. #45672 is narrower and tied to a specific model/module path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different root causes and different failure modes: torch.finfo(TypeError) on uint8 weights in audio modules versus AssertionError from llm_int8_skip_modules removing the default lm_head exclusion. 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": 17, + "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": "f6e1eb981b2d5914e3cebc0d8c22d011bb9afd6544ba674821e33e8d38a9649d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster contains two extremely sparse issue reports with unrelated personal-name-and-date titles. They do not look like duplicate bug reports; they look more like low-signal/spam entries.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45762 is the earliest issue and is no less representative than the other, but there is no evidence these two are the same underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45762 is the best cluster representative only because it is earlier; the pair does not appear to be a true duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Reject: the titles are different names/dates with no shared bug description, code path, or explicit linkage; they do not appear to be 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": 16, + "component_count": 17, + "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": "b21478d066a696f4f8d33b987830cc99e3cb128ee2e394a1af77d7ad1e3f0fb7", + "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": "The two closed issues are low-signal, name/date-only entries and do not describe the same bug, feature, or change. They should not be treated as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "The titles are different personal-name/date placeholders with no shared problem statement or code context, so they do not appear to represent 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": 17, + "component_count": 17, + "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-45869-5", + "nodes": [ + "issue:45869", + "issue:45870", + "issue:45871", + "issue:45872", + "issue:45873" + ], + "soft_pairs": [ + "issue:45869|issue:45870", + "issue:45869|issue:45871", + "issue:45870|issue:45871", + "issue:45870|issue:45872", + "issue:45870|issue:45873", + "issue:45871|issue:45872", + "issue:45871|issue:45873", + "issue:45872|issue:45873" + ], + "prepared_review_unit_hash": "6d7a66659b142f6dbae83a3964a0288c04d876e311248cbcd76da525026fd505", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5726, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5726, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster is not one single duplicate set: it splits into two exact-duplicate issue pairs (45870/45871 and 45872/45873). Issue 45869 is only loosely related by topic and does not look like a duplicate of either pair.", + "confidence": 0.93, + "canonical_issue_reason": "45870 is the clearest representative of the 'Example: Financial time series prediction with DataForge' thread because it is an exact duplicate of 45871 and has the strongest direct match in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "45870 is the best single issue to keep as the representative for one duplicate thread; it is an exact duplicate pair with 45871 and is more central than the loosely related dataset request in 45869.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Related financial/data topic, but the dataset bundle request and the DataForge example are different underlying issues." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Same as 45869 vs 45870: related theme, but not the same issue." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Same title and same apparent content; this looks like a direct duplicate." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "Both mention financial time series/DataForge, but one is an example request and the other is a scraping-service/project request; not the same concrete issue." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Related broad topic, but different request and likely different underlying change." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "Different issue themes; no sign they describe the same change or bug." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Different issue themes; only broad topical overlap." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Same title and same apparent content; this looks like a direct duplicate." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: 45870/45871 share the same title and metadata, as do 45872/45873, while 45869 is only topically similar. The conservative non-duplicate calls for the cross-pair comparisons are reasonable, and the representative selection of 45870 is supported by the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 27, + "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:43823", + "pull_request:41855|pull_request:43424", + "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:45213", + "pull_request:43995|pull_request:44827", + "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": "91835fef6af75baa179bcbcf202c904c00a740ccda03e139aa67c78d3cce734f", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35203, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35203, + "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 that happen to share broad surface areas (models, processors, docs, tests). The only clear duplicate-like pair is the two `fixed_cross_entropy` patches, which both address the same loss helper bug.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43251 is the best representative because it makes the concrete `fixed_cross_entropy` fix, explicitly targets issue 43240, and has the stronger discussion signal. PR 43254 is a near-duplicate alternative patch to the same function.", + "best_issue_reason": null, + "best_pr_reason": "PR 43251 is the most canonical PR in the set: it fixes a specific code-path bug, has an explicit issue link, and is more clearly scoped than the other PRs, which are feature additions, docs, or unrelated refactors.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Both are PRs, but one adds a new model and the other adds an Executorch dynamic-shape test; they do not fix the same concrete bug or change." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Tokenizer method additions for Mistral are unrelated to adding the MobileLLM model." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "A tokenizer API gap fix and an Executorch export test are different changes with no shared underlying defect." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor auto-loading robustness changes are unrelated to introducing MobileLLM." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Loss helper kwargs support is unrelated to the MobileLLM model addition." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "These touch different problems: cross-entropy kwargs vs Mistral4 test/model plumbing." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "Executorch dynamic-shape testing and Mistral4 fixes are not the same code-path problem." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Exportability tests for decoder-only LM are unrelated to the MobileLLM implementation." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "Adding MobileLLM and fixing config resolution order are separate changes with no shared bug." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "A new model implementation and Falcon output-collection refactoring are unrelated." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon output-capture refactoring is unrelated to the model-creation skill PR." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "These are different refactors/fixes in different model families and do not converge on one bug." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fixes and `layrnorm` renaming are unrelated code changes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "A Mistral4 fix and a docs-only audio/video processors PR are not the same underlying change." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 fixes and config-resolution-order changes address different issues." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "A model test/fix PR and a meta skill PR are not duplicates and do not share a concrete code-path fix." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "Adding MobileLLM is unrelated to the model-creation skill document update." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45795", + "accept": false, + "reason": "MobileLLM model code and docs for audio/video processors are unrelated changes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "Mistral4 test/fix work is unrelated to the docs-only audio/video processors update." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs patch the same `fixed_cross_entropy` helper for the same underlying issue (43240) and are plausible merge alternatives for the same code-path bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The judgments are grounded in the packet and stay conservative. The duplicate-like pair (43251, 43254) is a plausible same-bugfix alternative in `fixed_cross_entropy`, while the other pairs are reasonably rejected as different model additions, docs, refactors, or tests. The canonical PR choice for 43251 is also supported by the explicit issue link and focused scope." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 27, + "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": "52649b82458f527e64b55521406713ced11a8f4e6a0c1601ed29c920d1758f48", + "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": "Two related VibeVoice PRs, but they target different scopes: one adds the base VibeVoice model support, the other adds VibeVoice Realtime plus acoustic-tokenizer/runtime changes. They overlap heavily in files, but they are not the same concrete change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #40546 is the better canonical representative because it is the original, broader VibeVoice implementation and establishes the main model integration; #42781 is a later, narrower realtime extension built on top of it.", + "best_issue_reason": null, + "best_pr_reason": "PR #40546 is the best overall PR for this cluster since it covers the core VibeVoice addition with the widest surface area and is the natural anchor for the model family.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Shared VibeVoice integration files, but the PRs are not the same change: #40546 adds the base model, while #42781 adds realtime-specific behavior and acoustic-tokenizer/runtime support. They would not plausibly merge as one PR without conflating distinct features." + } + ] + }, + "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": 27, + "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": "cba1dac89ea94ae4e92a9716486bf9e7143deb81817bb886f411537891f898d9", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "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: TimesFM covariate forecasting vs. DINOv3 image classification support. They should not be clustered as duplicates.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "No true canonical PR for this cluster: the PRs target different code paths, different models, and different user-facing features.", + "best_issue_reason": null, + "best_pr_reason": "If one PR must represent the cluster, 41224 is the cleaner standalone feature PR because it has a narrow, well-defined DINOv3 classification support change and more review activity.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models and capabilities: TimesFM forecasting with covariates vs. DINOv3 image classification support. They do not fix or add the same underlying 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": 4, + "component_count": 27, + "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": 27, + "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": "ec40743887501281df6897b815cffc6509f118688384291a643505d9ebb03585", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10409, + "estimated_input_tokens": 2603, + "estimated_eval_tokens": 5462 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10409, + "estimated_input_tokens": 2603, + "estimated_eval_tokens": 5462 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-integration PRs (DeepSeek OCR, Isaac, Kimi2-6) that share boilerplate files but target different models and code paths. They should not be treated as duplicates or merged together.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different integrations for different models (DeepSeek OCR vs Isaac). Shared auto-mapping/docs scaffolding is expected boilerplate, not the same bug or change." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Different model additions with distinct implementations and files (Isaac vs Kimi2-6). Similar repository plumbing does not mean they fix or add the same concrete code path." + } + ] + }, + "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": 27, + "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": "3fcd693f7d6566343353b54b4caae4aab554b87add91a85badc69441b5e399d0", + "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": "Both PRs are broad GitHub Actions dependency bumps in workflow files, but they target different action families and different upgrade motives. They are related maintenance changes, not the same concrete change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: 42975 updates checkout/cache/upload-artifact for Node 24 compatibility, while 42976 updates docker/build-push-action and other release/build workflow actions.", + "best_issue_reason": null, + "best_pr_reason": "42975 is the cleaner representative of the cluster theme because its title and edits focus on a single compatibility-driven Actions upgrade, whereas 42976 is a separate dependency bump set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Different underlying changes: one upgrades core JS GitHub Actions for Node 24 compatibility, the other upgrades docker/build-push-action and related workflow actions. They are not the same bug/change 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": 7, + "component_count": 27, + "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": "099e1293db05055a827d781b2838e4d010f1e6b40fe5f9d34ccc46fe81dfaff8", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23535, + "estimated_input_tokens": 5884, + "estimated_eval_tokens": 12024 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23535, + "estimated_input_tokens": 5884, + "estimated_eval_tokens": 12024 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated model-addition PRs that only overlap on boilerplate files like docs/toctree and auto mappings. The only infrastructure PR ([Distributed] Add PP support natively) is also unrelated to the model PRs. No soft pair looks like the same underlying change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR 45838 is the strongest standalone PR in the set: it is a complete, self-contained model-support addition with docs, code, and tests. It is not a duplicate of the others, but it is the best representative PR here.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "ViT NEPA and Molmo are different model families; shared docs/auto-registry edits are boilerplate, not the same change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "ViT NEPA vs Molmo2 are separate model additions with different code paths and artifacts." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "ViT NEPA and CTSM are unrelated model implementations; overlap is only in shared registry/docs files." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are related by naming but are distinct models with different implementations and tests." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo and CTSM are unrelated model additions; no shared concrete bug or code-path change." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are different model families; similarity is limited to generic registration/docs updates." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45838", + "accept": false, + "reason": "Lfm2 Audio is an ASR/audio model add, while PP-OCRv6 is OCR text-recognition support; these are unrelated changes." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45838", + "accept": false, + "reason": "Native pipeline-parallel loading support is infrastructure work, not the same concrete model-support change as PP-OCRv6." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45838", + "accept": false, + "reason": "CTSM and PP-OCRv6 are unrelated model additions with different modalities 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": 8, + "component_count": 27, + "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": "a0a21a766c845498d64d13235b7f95e9cb7971a21d40568d9af54881b47d5e02", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates of one another. PR 44815 is a substantive dequantization fix across model-loading and FP8 code paths; PR 43291 is a Whisper tokenizer/test change; PR 43665 is test-only and appears unrelated to the other two. None of the soft edges should be accepted as the same underlying change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44815 is the strongest representative of the cluster because it is the only substantial production-code bugfix; the other PRs are narrow or test-only and cover different code paths.", + "best_issue_reason": null, + "best_pr_reason": "PR 44815 is the best single PR to keep as the cluster anchor because it has the clearest concrete fix and the broadest, most coherent implementation scope.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Whisper tokenizer/test changes and CLIP/ViT test edits are unrelated code paths; they do not fix the same bug and would not plausibly be one PR." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "One PR is Whisper decode/test cleanup, the other is FP8 dequant/model-loading work; different subsystems and different underlying problems." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "Test-only CLIP/ViT edits do not share a concrete bug or implementation path with the FP8 dequantization fix, so they should not be merged 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": 9, + "component_count": 27, + "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": "2dc2fd1a8079f505583325195722473cb110b253e4f7a4d33cc2f6325d265e68", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4562, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4562, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs are not duplicates: one is a synthetic setup/version/repo-bot check change, while the other is a broader CI/workflow and test-infra diff. The only overlap is a shared Vit test file, which is not enough to indicate the same underlying fix.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No clear canonical PR: 43488 is a narrow repo-bot/setup version test, while 43532 is a broader CI/workflow and testing-utils change; they do not represent the same change.", + "best_issue_reason": null, + "best_pr_reason": "43532 is the better representative PR only in the sense that it is the more substantial, multi-file change, but it is still not a duplicate of 43488.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Shared Vit test file aside, the diffs target different problems: 43488 adjusts setup/versioning for a bot check, while 43532 changes workflow and testing infrastructure. They are not the same code-path fix and would not be merged as 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": 10, + "component_count": 27, + "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": "e97d0845a9a11bbc950cfad8561ac8373c344bea4a0df2c63302453cde1103df", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6081, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6081, + "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 related but distinct feature PRs: one adds Promptable Concept Segmentation, the other adds Promptable Visual Segmentation. They share boilerplate/docs/pipeline-registry changes, but they target different pipelines and model integrations, so they should not be treated as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the two pull requests implement different segmentation pipelines with different model support and task docs.", + "best_issue_reason": null, + "best_pr_reason": "PR 43613 is the broader of the two and touches more model integrations, but it is still a separate feature from 43612, not a duplicate.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Different concrete changes: promptable concept segmentation vs promptable visual segmentation. Shared scaffolding and docs do not make them the same underlying fix or 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": 27, + "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": "87092bbea97112da3a4ba67afe6c3cab436364d77999ed5fe212710f17f4f72b", + "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": "Both pull requests modify `src/transformers/trainer.py`, but they address different trainer extension points: one changes gradient-accumulation loss scaling, the other refactors signature/column filtering for PEFT models. Shared filename alone is not enough to treat them as the same change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43651 is the better representative anchor because it introduces a clear, self-contained trainer behavior hook (`_loss_is_scaled_for_ga`) and changes the training-step loss scaling path; however, it is not a duplicate of 43663.", + "best_issue_reason": null, + "best_pr_reason": "PR 43651 is the stronger standalone PR for the cluster only by being the more explicit behavior change. PR 43663 is a separate override hook for signature-column filtering and should not be merged with 43651 as the same fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Different concrete code paths and extension goals: gradient-accumulation loss scaling vs. signature column filtering for PEFT/custom trainers. They share a file, not a bug or 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": 12, + "component_count": 27, + "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": "c45245388f8300ce91a42ac5e2fb737d0c2943283e5b7101e62e6e8c7386bfe3", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two PRs (43836 and 43842) are near-duplicates for the same TypeAdapter runtime-import NameError in `src/transformers/cli/serve.py`; 43656 looks related but is broader and less clearly the same concrete fix.", + "confidence": 0.74, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43842 is the cleanest, most targeted fix for the `TypeAdapter` NameError: it explicitly guards the `pydantic` import with `TYPE_CHECKING` and quotes the annotation, directly addressing the runtime import problem with minimal scope.", + "best_issue_reason": null, + "best_pr_reason": "PR 43842 is the best representative of the cluster because it most directly and narrowly fixes the runtime `TypeAdapter` annotation issue in the CLI serve code path.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "Both mention `TypeAdapter` in `cli/serve.py`, but 43656 appears to be a broader typing cleanup with additional annotation changes and a different issue target; the evidence is not strong enough that they fix the exact same concrete bug." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "These are alternative implementations of the same fix for the same runtime `TypeAdapter` NameError in `src/transformers/cli/serve.py`, and both target the same issue, so they look duplicate-equivalent." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: 43836 and 43842 share the same explicit issue target (43824) and both modify the same file to address the TypeAdapter import/annotation runtime problem, while 43656 has a different issue target (43576) and only soft similarity. The soft-edge verdicts are conservative enough." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 27, + "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": 27, + "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:44066|pull_request:44071", + "pull_request:44018|pull_request:44068", + "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:44722", + "pull_request:44068|pull_request:44116", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44116", + "pull_request:44018|pull_request:44085", + "pull_request:44018|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44068|pull_request:44086", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request:44098|pull_request:44101", + "pull_request:44059|pull_request:44722", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44161", + "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:44056|pull_request:44101", + "pull_request:44073|pull_request:44161", + "pull_request:44059|pull_request:44068", + "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:44018|pull_request:44129", + "pull_request:44010|pull_request:44073", + "pull_request:43997|pull_request:44074", + "pull_request:43997|pull_request:44129", + "pull_request:44071|pull_request:44129", + "pull_request:44010|pull_request:44018", + "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": "7c39461dba1b542d6d2703a92e226bd07805ef58d023d6718ebe19da8a4d5301", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84899, + "estimated_input_tokens": 21225, + "estimated_eval_tokens": 42706 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75093, + "estimated_input_tokens": 18774, + "estimated_eval_tokens": 37804 + }, + "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 around standardized output tracing, but most pairs are not true duplicates because they touch different model families and code paths. The only clear duplicate groups are the GPT-J/CodeGen refactors and the GPT-Neo refactors.", + "confidence": 0.83, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44066 is the best representative: it has an explicit issue link, covers the core GPT-J/CodeGen output-tracing refactor, and is the broadest coherent version of that same concrete change.", + "best_issue_reason": null, + "best_pr_reason": "PR 44066 is the strongest global representative for this cluster because it centers the shared GPT-J/CodeGen output-tracing change with issue linkage, while most other items are narrower or on unrelated models.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families and code paths (FNet/CVT vs GPT-J); only the output-tracing theme overlaps." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different model families and code paths; not the same bug or change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Same GPT-J output-tracing refactor on the same code path; one PR could plausibly absorb the other." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "Different CNN model implementations and refactor scopes; same broad theme only." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet vs GPT-J/CodeGen are unrelated code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen and EfficientNet are unrelated concrete changes." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa are unrelated model paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen refactor vs MGP-STR refactor; different models and implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are unrelated code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Same GPT-Neo output-tracing refactor on the same model file; these look like duplicate/iterative versions of one change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen vs GPT-Neo; same topic, different concrete model code." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and RegNet are different model families and changes." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "RegNet vs GPT-J/CodeGen; unrelated code paths." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J are unrelated implementations." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "RegNet vs GPT-J; not the same concrete refactor." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo vs MPT are different model code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "MPT and MGP-STR are unrelated changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen; same broad theme but different model code." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert are unrelated model implementations." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44116", + "accept": false, + "reason": "MPT vs Flaubert/XLM are unrelated code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44059", + "accept": false, + "reason": "GPT-Neo vs GPT-2 are different model-specific refactors." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J vs MGP-STR; unrelated models and code paths." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are different model families." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "RegNet vs MPT; unrelated concrete changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR; different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44059", + "accept": false, + "reason": "GPT-Neo and GPT-2 are separate model implementations." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT vs ImageGPT; unrelated model code." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo vs MPT; different code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "MPT vs MGP-STR; unrelated changes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-2 vs GPT-Neo are different model-specific refactors." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "Segformer vs GPT-J/CodeGen; not the same bug or change." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are unrelated model code paths." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "VisualBert vs LongT5; different implementations." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-2 and MPT are unrelated model refactors." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44071", + "accept": false, + "reason": "MPNet vs MPT; different code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet vs Segformer are different models." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBert and MPT are unrelated changes." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert vs VisualBert; different model code." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44074", + "accept": false, + "reason": "Segformer and TextNet are unrelated model-specific refactors." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert and Flaubert/XLM are different code paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 vs MGP-STR; unrelated model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo and SpeechT5 are unrelated changes." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet vs LongT5; different model code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet and TextNet are unrelated model families." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44068", + "accept": false, + "reason": "MPNet vs GPT-Neo; same theme, different concrete change." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT vs ImageGPT; unrelated implementations." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44129", + "accept": false, + "reason": "TextNet and SpeechT5 are different model paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo vs GPT-J; not the same model-specific refactor." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBert and DeBERTa are unrelated code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa vs TextNet; different model families." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPT-J/CodeGen standardized output-tracing refactor on the same code path; these are mergeable duplicates." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors on the same file; one is a narrower version of the same change." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J vs SpeechT5 are unrelated model implementations." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "FNet/CVT vs RegNet/ResNet/RT-DETR; different concrete changes." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "FNet/CVT and SpeechT5 are unrelated model code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa vs SpeechT5; not the same bug or change." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa and VITS are unrelated model implementations." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The rejected soft-edge pairs are mostly clearly cross-model or cross-family, and the accepted pairs are the only ones that plausibly look like the same mergeable bugfix (GPT-J/CodeGen and GPT-Neo refactors)." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 27, + "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": "f8289d5d8bf2c29c753919e576ebb1aaef62317e4a6a4a3d23943021fe71c3fe", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84899, + "estimated_input_tokens": 21225, + "estimated_eval_tokens": 42706 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17127, + "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 are all model-specific refactors to adopt standardized output capturing/decorators, but they touch different model code paths and are not duplicates of one another. The shared theme is architectural cleanup, not one underlying bug or change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "Best representative is PR 44073: it shows the standard pattern clearly in a single model file and is a straightforward example of the output-tracing refactor theme.", + "best_issue_reason": null, + "best_pr_reason": "PR 44073 is the cleanest representative of the cluster\u2019s refactor pattern; however, none of these PRs are mergeable as duplicates because each targets a different model implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Both are output-tracing refactors, but they modify different models (FocalNet vs ImageGPT) and different concrete code paths. Same maintenance theme, not the same change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Both move models toward standardized output capture, but VisualBERT and TextNet are separate implementations with different refactor details and tests. Not one underlying bug/change." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet and VisualBERT each change their own output-capture wiring. The similarity is the refactor pattern, not shared functionality or a single fix." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "These are separate model refactors in unrelated code paths; they do not look like one PR could plausibly subsume the other." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBERT are distinct models with different output-handling implementations. The overlap is only the standardized decorator migration." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBERT and SpeechT5 both touch output tracing, but they target different layers/models and different concrete behavior. They are not 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": 15, + "component_count": 27, + "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": "ddf9bec995d1bc564e0707151d74a449bd1d51e489547a2df6f70c93c21daf91", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40179, + "estimated_input_tokens": 10045, + "estimated_eval_tokens": 20346 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40179, + "estimated_input_tokens": 10045, + "estimated_eval_tokens": 20346 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is a set of similarly titled but model-specific PRs refactoring output tracing across unrelated architectures. They share the same general theme, but not the same concrete code path, so none of the soft edges should be treated as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single true canonical PR: each PR targets a different model implementation. If a representative is needed, 44025 is the broadest example because it spans two closely related Depth Anything files, but it is not a duplicate of the others.", + "best_issue_reason": null, + "best_pr_reason": "44025 is the strongest representative of the theme because it has the broadest local scope and clear output-tracing refactor work, but the set is not a duplicate cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families and files (timm_backbone vs upernet); same refactor theme only, not the same code-path change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Different architectures and modules (timm_backbone vs vision_text_dual_encoder); only the refactor pattern matches." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different model implementations (timm_backbone vs univnet); not the same concrete bug or change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "timm_backbone and mamba/falcon_mamba are unrelated code paths; too broad to be duplicates." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Different models and output logic; similarity is only at the generic tracing-refactor level." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "MobileNetV1 and UnivNet are unrelated models; same refactor motif, not the same fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families and changed files; no shared concrete code path." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "MobileNetV1 and Depth Anything are unrelated model implementations; do not merge on theme alone." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Different wrapper/model code paths; both are output-tracing refactors only in a broad sense." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "MobileNetV1 vs speech_encoder_decoder are different code paths; 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 code paths; same refactor style only." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different architectures (vision-text dual encoder vs upernet); no duplicate evidence beyond output-tracing cleanup." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model families and files; not plausibly one merged PR." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Distinct model implementations and code paths; generic similarity is insufficient." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "UnivNet and UperNet are unrelated models; same refactor pattern only." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "UnivNet vs Mamba/Falcon Mamba are different code paths; not the same concrete fix." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model implementations; no shared bug or change beyond refactoring output capture." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "UperNet and RWKV are unrelated architectures; not the same underlying issue." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model families and changed files; too broad to merge as duplicates." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "Mamba/Falcon Mamba vs SuperPoint are unrelated code paths; same refactor pattern only." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model implementations and semantics; not the same concrete bug or change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Timm backbone and CodeGen are unrelated code paths; output-tracing cleanup alone is not enough." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "UnivNet and CodeGen are unrelated models; not a duplicate change." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "UperNet and CodeGen are unrelated implementations; same broad refactor theme only." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Vision-text dual encoder and CodeGen are different code paths; do not conflate on pattern similarity." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Depth Anything and VisionEncoderDecoder are different model code paths; not the same fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Depth Anything vs SpeechEncoderDecoder are unrelated architectures; similarity is only at the refactor level." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Depth Anything and SuperPoint are distinct model implementations; not duplicates." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Depth Anything and RWKV are unrelated code paths; no shared concrete bug." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "Depth Anything and DPR are different model families; not the same underlying change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "VisionEncoderDecoder and RWKV are unrelated implementations; generic tracing refactor only." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "VisionEncoderDecoder vs SpeechEncoderDecoder are separate wrappers and code paths; not a duplicate." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Different models and semantics; same high-level refactor theme is insufficient." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "VisionEncoderDecoder and DPR are unrelated code paths; not the same bug or change." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated model implementations; not mergeable as one PR." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "SpeechEncoderDecoder and RWKV are different code paths; only broadly similar output-tracing cleanup." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "SpeechEncoderDecoder and DPR are unrelated models; no duplicate evidence." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are unrelated architectures; not the same concrete fix." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "SuperPoint and DPR are different model code paths; too broad to merge." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are unrelated models; same refactor motif only." + } + ] + }, + "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": 27, + "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": "a669c2b166671136c6245af9bbf42af40a65f874efe9c88c81a3bd9541133dcf", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-integration PRs that only overlap on shared Transformers boilerplate (docs, auto maps, package registration). They target different models and different implementation code paths, so they should not be deduplicated together.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the PRs add different models (PenguinVL, DeepSeek-OCR-2, Voxtral TTS) rather than the same fix or feature.", + "best_issue_reason": null, + "best_pr_reason": "No single PR is a duplicate-matching canonical choice; if forced, none of these is a better representative than the others because they are distinct additions.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different model families and code paths: PenguinVL vs Voxtral TTS. Shared auto-registration/doc scaffolding is not enough to treat them as the same change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "PenguinVL and DeepSeek-OCR-2 are separate model implementations with different files, configs, and tests; they only share generic Transformers integration boilerplate." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are unrelated model additions; the overlap is limited to common framework plumbing, not a shared bug or mergeable 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": 17, + "component_count": 27, + "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": "47b213b641135d53d46a56ff5512841aa2b9f93c37f0609ddaad12d39c9864b2", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4408, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4408, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two related but distinct pull requests about fusion machinery: one introduces a standalone Module Fusion API, while the other adds KernelConfig-based n-to-1 kernel fusion integration. They share the same broad theme but are not the same change.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #44979 is the cleaner canonical representative of the cluster because it introduces the core Module Fusion API itself and dedicated tests, whereas #45363 is a separate KernelConfig-based integration/follow-up feature.", + "best_issue_reason": null, + "best_pr_reason": "PR #44979 is the best overall anchor for this cluster: it is the most foundational and self-contained fusion API change, with a clearer core abstraction than the more specific integration-oriented PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Not a duplicate: #44979 adds a new Module Fusion API in src/transformers/module_fusion.py, while #45363 implements n-to-1 kernel fusion via KernelConfig across integrations/modeling utilities. Same general area, but different concrete code paths and mergeable as separate PRs." + } + ] + }, + "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": 27, + "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": "813d3968a95b60d92103e2a713329349603a5f3c0c8e3a3df9035ed10e04c1f4", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4413, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4413, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same AttributeError in `_patch_mistral_regex` by switching from `backend_tokenizer.pre_tokenizer` to `tokenizer.pre_tokenizer` on the same code path; 45317 is the more complete patch because it adds tests.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:45317 is the better canonical PR: it fixes the same bug as 45086 and includes test coverage, making it the more complete change set.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:45317 is the strongest overall PR candidate because it targets the same concrete fix and adds verification tests.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same underlying AttributeError fix in `_patch_mistral_regex` on the same line-level code path; 45317 is essentially the test-backed version of 45086." + } + ] + }, + "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": 27, + "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": "b300943dd8c077366de12d30b0175623503f631d705351aa2a4a20d23eb0d395", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6065, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6065, + "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 PRs touch the Nemotron H family, but they are not the same change: one refactors the base NemotronH conversion/model wiring, while the other splits Nemotron H into dedicated dense/sparse model variants and updates docs/tests.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45569 is the better canonical representative because it makes the larger, user-facing architectural change: it adds dedicated NemotronHDense/NemotronHSparse implementations, updates auto-mapping and docs, and includes tests. PR #45115 is a narrower refactor focused on inheritance and conversion mapping.", + "best_issue_reason": null, + "best_pr_reason": "PR #45569 is the strongest standalone PR in this cluster: it is broader, more complete, and defines the new model variants rather than only adjusting internal refactor/conversion behavior.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "They overlap on NemotronH internals, but #45115 is a targeted refactor/conversion-mapping change while #45569 introduces separate dense/sparse model classes plus docs/tests. They are related, not the same concrete fix or mergeable duplicate." + } + ] + }, + "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": 27, + "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": "91687fd88fd34a50a5924668adad801021097794aef37634c691623be60c9ac5", + "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": "Two related but distinct feature PRs: one adds per-layer heterogeneous config plumbing, the other adds broader heterogeneous model/runtime support. They overlap in shared config helpers and tests, but they are not the same underlying change.", + "confidence": 0.81, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45332 is the broader, more central change: it extends heterogeneous support into cache/modeling code paths and includes the config integration needed for runtime use.", + "best_issue_reason": null, + "best_pr_reason": "PR 45332 is the best representative because it covers the end-to-end heterogeneous model support, while PR 45333 is narrower config-only plumbing that looks like a component of the larger feature.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "They share heterogeneous config helpers, but one is a config-layer PR and the other is a broader modeling/runtime PR. They touch related infrastructure, not the same concrete bug or mergeable 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": 21, + "component_count": 27, + "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": "e5c9f75a66569ee4b7630071ed8aea8cb1c35ae12983fa93c75d87ecad772e36", + "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": "These are both typing-related PRs, but they address different concrete changes: one is a broad type-checking sweep across many transformer modules, the other adds shared typing aliases/protocols and related model utility updates. They are similar in theme but not duplicates.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45415 is the broader umbrella typing sweep and is the more representative canonical PR for this cluster; PR 45425 is a narrower follow-up focused on shared typing helpers and related model utility adaptations.", + "best_issue_reason": null, + "best_pr_reason": "PR 45415 is the best overall representative because it covers the wider type-checking effort across `src/transformers/*py`, whereas PR 45425 is a more specialized support change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Same general typing initiative, but not the same underlying change. 45415 is a broad per-file typing cleanup; 45425 introduces shared typing protocols/aliases and utility updates. They would not naturally merge into one PR without conflating distinct work." + } + ] + }, + "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": 27, + "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-45487-6", + "nodes": [ + "pull_request:45487", + "pull_request:45817", + "pull_request:45843", + "pull_request:45858", + "pull_request:45890", + "pull_request:45926" + ], + "soft_pairs": [ + "pull_request:45487|pull_request:45843", + "pull_request:45487|pull_request:45926", + "pull_request:45817|pull_request:45843", + "pull_request:45858|pull_request:45890", + "pull_request:45858|pull_request:45926", + "pull_request:45890|pull_request:45926" + ], + "prepared_review_unit_hash": "d8f7e8e45f5618f4dd5268bd5980e2cabd5dfdddee41c9ae38224ab1fc10bf92", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 6, + "serialized_chars": 14720, + "estimated_input_tokens": 3680, + "estimated_eval_tokens": 7616 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 6, + "serialized_chars": 14720, + "estimated_input_tokens": 3680, + "estimated_eval_tokens": 7616 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are mostly unrelated model-parallel fixes or model-specific XPU test expectation updates. None are true duplicates of each other; the only broad resemblance is that several touch device-placement/model-parallel behavior or add XPU test data, but they target different models and code paths.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "No PR here is a clear duplicate of another. If one must be the cluster representative, #45487 is the broadest substantive fix and the most likely source of the shared model-parallel theme across the set.", + "best_issue_reason": null, + "best_pr_reason": "#45487 is the strongest representative because it fixes a real model-parallel bug across several model implementations, while the others are narrower, model-specific fixes or test-only expectation updates.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45843", + "accept": false, + "reason": "Both are model-parallel themed, but they target different models and different code paths. Not the same concrete bug." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45926", + "accept": false, + "reason": "AltCLIP/ChineseCLIP model-parallel fixes are unrelated to HyperCLOVAX XPU test expectations." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45843", + "accept": false, + "reason": "Gemma4 parallel fixes and DEIMv2 parallel fixes are separate model implementations with different changes; too broad to merge as one duplicate." + }, + { + "left": "pull_request:45858", + "right": "pull_request:45890", + "accept": false, + "reason": "Both are test-only XPU expectation updates, but for different models and different logits; not the same underlying change." + }, + { + "left": "pull_request:45858", + "right": "pull_request:45926", + "accept": false, + "reason": "Different model test suites with separate expected outputs; they do not fix the same concrete issue." + }, + { + "left": "pull_request:45890", + "right": "pull_request:45926", + "accept": false, + "reason": "Both update XPU expectations, but for different model-specific tests and values; not a duplicate 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": 23, + "component_count": 27, + "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": "f11aef75637129d1066526d9c6c55b5f3909f7f6eab4b93aa67c809efc62d0d3", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two separate EP-related loading fixes: 45548 preserves distributed_config and adds has_ep, while 45662 fixes DTensor/EP parameter loading so experts are not overwritten during load. They overlap in modeling_utils but target different code paths and failure modes.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "45662 is the more concrete and complete fix for the actual parameter-loading overwrite path, with coordinated changes across loading and MoE/tensor-parallel code.", + "best_issue_reason": null, + "best_pr_reason": "45662 is the stronger representative PR because it addresses a specific runtime corruption bug rather than only plumbing for EP configuration.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Both involve expert parallelism, but 45548 fixes config serialization/feature detection for ZeRO-3 loading, while 45662 fixes a different DTensor/FSDP2 overwrite issue during parameter assignment. They would not plausibly 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": 24, + "component_count": 27, + "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": "9e6b0e7b45812b0f96e8705d7e5840e85af89d12216835e950352fadd7042def", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4589, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4589, + "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 target the same xdist/captured_info debugging-log problem under issue 45561; PR 45645 is the broader, more complete fix and subsumes the core change in 45639.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45645 is the best canonical representative because it includes the same testing_utils xdist-safe fix as 45639 and also updates the CI/workflow handling needed to preserve and aggregate the new per-worker log files.", + "best_issue_reason": null, + "best_pr_reason": "PR 45645 is the strongest overall candidate: it addresses the same concrete bug and extends the fix to the CI artifact-consumption path, making it the more complete merge target than 45639.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Accepted: both are about making captured_info debug logs safe under xdist for the same issue. 45645 appears to be a superset/broader implementation of the same underlying change, not a different 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": 27, + "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": 27, + "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 + }, + { + "label": "pull_request", + "component_index": 27, + "component_count": 27, + "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-45997-2", + "nodes": [ + "pull_request:45997", + "pull_request:46005" + ], + "soft_pairs": [ + "pull_request:45997|pull_request:46005" + ], + "prepared_review_unit_hash": "b1e17f5872fa5ba5683d68b4536022260189b774c7064f68fa2df4cd6bd51629", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4240, + "estimated_input_tokens": 1060, + "estimated_eval_tokens": 2376 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4240, + "estimated_input_tokens": 1060, + "estimated_eval_tokens": 2376 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same StaticLayer cache-length typing bug in `src/transformers/cache_utils.py` and target the same issue. PR 46005 is the more complete fix because it both scalarizes `cumulative_length` and normalizes `get_seq_length()` to return a plain int.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "`pull_request:46005` is the better canonical PR: it contains the core data-shape fix plus the API-side `get_seq_length().item()` correction, so it fully resolves the int-vs-tensor mismatch rather than only changing the stored tensor shape.", + "best_issue_reason": null, + "best_pr_reason": "`pull_request:46005` is the best PR overall because it directly fixes the reported behavior end-to-end and is strictly more complete than `pull_request:45997`.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45997", + "right": "pull_request:46005", + "accept": true, + "reason": "Same underlying bug in the same code path (`StaticLayer` cache length handling); the second PR is a superset-style refinement of the first, and they could plausibly be merged into one change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/manifest.json b/snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..20eda44c4bd24dab4f9943a922afadd451f3e5d5 --- /dev/null +++ b/snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260517t060024z", + "artifacts": { + "hybrid": "snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-17T06:03:48Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260517T060024Z", + "variant": "hybrid" +} diff --git a/snapshots/20260517T060024Z/manifest.json b/snapshots/20260517T060024Z/manifest.json index 5166c5b0540616f7530047b6e02bbdd51c80a0ae..86dd3fe370e2e5bff2330208a0bfe63d78228f3e 100644 --- a/snapshots/20260517T060024Z/manifest.json +++ b/snapshots/20260517T060024Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 241 }, "extracted_at": "2026-05-17T06:00:24Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260517t060024z", + "runs": { + "hybrid-model-20260517t060024z": { + "analysis_id": "hybrid-model-20260517t060024z", + "artifacts": { + "hybrid": "snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260517T060024Z/analysis-runs/hybrid-model-20260517t060024z/manifest.json", + "model": null, + "published_at": "2026-05-17T06:03:48Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260517T060024Z", "watermark": {